Free Essay

Forecasting the Quarterly Rice Production in the Province of Iloilo Using Different Forecasting Models

In: Business and Management

Submitted By aine2014
Words 8603
Pages 35
CHAPTER I
INTRODUCTION
Brief Background
“Rice,” first used in the middle of the 13th century, undergoes a long journey on derivation of its name. It is written to have originated from the Old French, “ris,” which came from the Italian “riso,” which in turn from the Latin “oriza.” Despite having a series of appellation, rice is simply the seed of the monocot plants Oryzasativa (Asian rice) or Oryzaglaberrima (African rice), considered to be the most utterly consumed staple food for a vast portion of the world’s human population, specifically in Asia and the second-highest with the most number of production, after corn, based on the 2010 data of FAOSTAT, the Food and Agricultural Organization of the United Nations.

Notwithstanding the association, Oryzasativaand Oryzaglaberrimaare two different species. The former is more predominantly acknowledged than the latter because of its popularity in cereal biology. Great subspecies with variety of kinds have been widely generated because of its easy genetic modification for the reason that it contains the largest genome, consisting of 430 Mb across 12 chromosomes, among the cereal plant(Linares, 2002).

One of its speciesis the sticky, short grained Japonica or Sinica variety, usually cultivated in dry fields, in temperate East Asia, upland areas of Southeast Asia and high elevations in South Asia. Second is the non-stick, long-grained Indica varietywhich is mainly lowland rice, grown mostly submerged, throughout tropical Asia. And the third is the broad-grained rice, thrives under tropical conditions, initially called as Javanica, but is now known as Tropical Japonica. Example of thisinclude the medium grain 'Tinawon' and 'Unoy' cultivars, which are grown in the high-elevation rice terraces of the Cordillera Mountains of Northern Luzon. Apart from these subspecies, Oryzasativa is also famous for its assortment of colors: the white rice, brown rice, black rice, purple rice and red rice(Linares, 2002).

On the contrary, while Oryzasativa is a potent specie,Oryzaglaberrimais a domesticated one. It is believed to have been domesticated 2000–3000 years ago. This species often show more tolerance to fluctuations in water depth, iron toxicity, infertile soils, severe climatic conditions and human neglect, and exhibits better resistance to various pests and diseases. However, it also manifestswith it negative characteristics as regards to the Asian rice, namely; the brittleness of its grain and the crackling during industrial polishing, not to mention its lower yields. Thus, scholars have been continuously breeding up the two to produce a better rice for the African society.

Nonetheless, even with the disparity between the two species, its contribution to mankind is still immeasurable. Aside from being just a food to satisfy hunger, it is after all the most important grain for survival with regard to human nutrition and caloric intake, providing half of the calorie requirements, one-third of protein intake, and more than one-fifth of the calories consumed worldwide by humans.Moreover, its unparalleled effect on small farmers who cultivate it on millions of hectares throughout the region is very strong. This is not only directed towards poverty alleviation and sustenance but the heightened call on increasing agricultural population is very prominent. With the ballooning population, there is a very high pressure on increasing the production of the already strained food-producing sources in every country and region.

In the Philippines, rice is locally known as palay, bigas, and kanin. It is the food that is rarely ever missing on the table, be it breakfast, lunch or dinner. A Filipino meal cannot be complete without it, even amidst huge gatherings and regardless of a resplendent menu. Even when it comes to merienda or snacks, rice is the Philippines’ staple food.However, for a small country like ours, consumption is not always correlated with production. Even though Filipinos are certified rice-eaters, considering the country’s burgeoning population, we arestill inclined to import rice from other countries. This is due to the fact that the Philippines’ area that harvests rice is very small compared with major rice-producing countries in Asia. Although the country is agricultural in nature, it does not have the large land resource to produce the total rice requirement. The Philippines has only 4.46 million hectares (according to the 2008 data) and we are to feed 20 persons per hectare of area harvested to rice as compared to Thailand and Vietnam that only feed 7 and 12 persons per hectare, respectively (BAR, 2012).

All of the things mentioned above have direct effect on the pursuit of this study in determining the future quarterly production of palay in the next succeeding years which will bear huge impact for the country’s effort on pursuing a hundred percent healthy and full citizens.

Rationale of the Study
According to FAO Stat, 2009, the Philippines is the 8th largest rice producer in the world, accounting for 2.8% of global rice production and the largest rice importer in 2010. Rice, being the most important food crop in the country has a production of as nearly as 15.7 million metric tons of palay (pre-husked rice) in 2010, produced extensively in Luzon, the Western Visayas with 3.25 to 5.20 metric tons per hectare coming from Iloilo City, Southern Mindanao and Central Mindanao. Additionally, in the same year, it accounted for 21.86 percent of gross value added in agriculture and 2.37% of GNP.

In lieu with this is the expected increase of population of the Philippines to more than 100 million in 2014 according to Commission on Population (PopCom) based on the records of the estimated current population of the country that is around 98.9 million. And from this, Iloilo Province is set to hit 1.950M population this yearwith the highest record on Passi City.

This study provides greater emphasis on the quarterly rice production of Iloilo province for the past 10 years starting from the first quarter of 2004. The rationale behind this is that with the growing population expected to hit in the Province, there is an urgent need that rice production must be carefully monitored to have a better grasp on the proper allocation and distribution of this scarce resource among Ilonggos. It is impractical to settle in a country, city or province filled with malnourished and ill-fitted individuals, but rather it is more felicitous to mingle with lively, kicking and happy people. With the rising development and expansion brought about by high surge of investments pouring in Iloilo, it is but proper to couple it with improving rice production. And if any case that a deficiency occurs or a shortage for that matter, precautionary measures will be established earlieror recommended actions be implemented to curb the issue beforehand so as not to provide haste and conflict when the time comes.

Statement of the Problem
With these threats bound to commence if these symptoms will not be properly addressed, there will be no one left to suffer but the Filipino people themselves. Everybody knows how important rice to every human beings alive; as mentioned above, it is the food for survival, so just an inkling of inadequacy means a bigger problem of scarcity. Thus, this paper focuses on forecasting the quarterly production of palay in Iloilo Province with the use of some forecasting techniques. While it may be easier to estimate production by the use of personal judgment, yet it is more accurate to apply these forecasting techniques. Forecasting production is a critical subject to endure, since a slight decline or lowering steadily suggests an imperative move to review all the inherent deficiencies occurring as to why such happens. Moreover, this paper also addresses the question on the sufficiency of palay to compete with the swelling population of the province because from these forecasted figures, the Iloilo government can heighten their awareness on the issue and eventually make the appropriate actions.

Variables used in this paper involves the actual quarterly palay production for 10 years starting from the first quarter of 2004. So, overall there is a total of 40 periods incorporated in this paper. Throughout this study, palay pertains to rice as well as rice refers to palay.

CHAPTER II
Objectives of the Study

Generally, this study aims to determine the quarterly rice production in the Province of Iloilo from 2004 to 2013 using different forecasting techniques.

Iloilo, being one of the country's top ten achievers in rice production (SunStar, 2012) and with its promising export-potential rice quality production according to Agriculture Secretary Proceso Alcala (The Daily Guardian, 2012), it is vital that its rice production is closely monitored. This study aims to provide forecasts that would aid different sectors in society, particularly in the said province, in making important decisions related to the production of rice. Specifically, the forecasts obtained can:

* Help monitor trends of rice production on a quarterly basis. * Provide benchmark (target) as to how much should be produced in the succeeding periods. * Provide relevant information to the government for its future decision making as to the need for rice importation or the possibility of rice exportation, for additional revenues. * Help identify periods having relatively low rice production and have it properly addressed b y the appropriate government agency. * Help determine whether the province is self-sufficient in its supply of rice. * Help ascertain whether rice production capacity for a particular period can aid in supplying for other provinces deficiency in rice supply. * Help provide basis as to whether rice production growth can keep up with population growth in the province.

CHAPTER III
METHODOLOGY
To make this study feasible and systematic, the authors have undertaken certain procedures starting from the collection of data, testing the variables tocomputing forecasting figures through the use of forecasting techniques.

Collection of Data
Data information and figures were primarily obtained through online sources. The website countrystat.bas.gov.ph provides the comprehensive statistics on the production of different agricultural products such as crops, poultry, feedstock, etc. This website is spearheadedby the Philippine Statistics Authority which gives timely, accurate, relevant and useful data especially regarding statistics, as the name suggests, for the government and the public for decision-making. FAO Stat of the United Nations, an international website were also used to obtain comparisons as to the production, trade and food supply from different countries which are valuable members of the United Nations. FAO is basically an agency that leads international effort to defeat hunger. They are the source of knowledge and information that helps countries in modernizing and improving agriculture, forestry and fisheries practices, ensuring good nutrition and food security for all.

Testing for Seasonality
As practiced by other rice-producing countries as well as in the Philippines, due to the different varieties of rice emerging in the market, there is no assurance that it will be harvested or reaped in the same time of the year. While some harvest it in February and March just like in Vietnam, others reaped it in some time in September—November like in India. However, in the Philippines, though it may seem that the country is harvesting throughout the year, production is strong on every 3rd quarter of the year. With this qualitative forecasting, the authors can say that rice exhibit seasonality, but for the sake of more accurate and reliable forecasting, a quantitative estimation is a must to see if really rice exhibits seasonality which needs to be subjected to decomposition to separate the time series into its component parts.
Seasonal time series contain a pattern itself, at least approximately, each year (Levin, 2001). Thus, there is a need for illustration of the quarterly production of palay for the determination of the highest and lowest points of each year; and this can be done through the use of a chart. If the points identified occur in about the same periods, then the data points are seasonal and these are subject to decomposition method.

Figure 1. Quarterly Palay Production, 2004-2013 Year | Peak (High) | Trough (Low) | 2004 | Quarter 3 | Quarter 2 | 2005 | Quarter 4 | Quarter 2 | 2006 | Quarter 3 | Quarter 2 | 2007 | Quarter 3 | Quarter 2 | 2008 | Quarter 3 | Quarter 2 | 2009 | Quarter 3 | Quarter 2 | 2010 | Quarter 4 | Quarter 2 | 2011 | Quarter 3 | Quarter 2 | 2012 | Quarter 3 | Quarter 2 | 2013 | Quarter 3 | Quarter 2 |

Table 1. Peaks and Troughs of Quarterly Production in Years 2004-2013

Table 1 makes the summary of the points presented in Figure 1 with respect to the highest and lowest points of production of each year. As depicted from both illustrations and as stated in the preceding paragraphs, the peaks and troughs are consistent. Although, there is somewhat a deviation in the peak of years 2005 and 2010, the remaining years or say, majority of the years conform with the same peak which is quarter 3. Hence, since the data points are consistent, the production points will be deseasonalized and be subject to decomposition method.

Data Analysis
Exploration of this study will not be possible without utilizing some tools that will make the work on forecasting easier. Whereas it can be done through manual computation, the Microsoft excel is a better choice, if not the best. Six forecasting techniques are integrated in this paper to better predict the future production based on the past; and in each technique, the Mean Absolute Deviation (MAD), Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE) are computed to determine the accuracy of each forecast.
MAD, MSE and MAPE are calculated by using the following formulas:

Where: Forecast Error/ Error = Actual value—Forecast value

MAD weighs all errors evenly. MSE weighs errors according to their squared values and MAPE weighs according to relative error.

The six time-series models are the following: A. Naïve Forecasting
This is the most cost-effective objective forecasting model, and provides a benchmark against the more sophisticated models. An estimating technique in which the last period’s actuals are used as this period’s forecast, without adjusting them or attempting to establish causal factors. Thus, the last quarter’s productions are this current period’s productions. It is exhibited by the formula below:
Ft+1 = Yt
Where:
t+1= Forecast for the next quarter t = Observed value for the quarter

B. Simple Moving Average
The model is commonly used with time series data to smooth out short-term fluctuations and highlight long-term trends or cycles. This is calculated to analyze points by creating a series of averages of different subsets of full data sets where the most recent period of data is added and the oldest is dropped. In this paper, the 4-quarter simple moving average is used because within this period, a lower MAD is obtained. (See Appendices) This is completed by using the formula:
Ft+1 = (Yt + Yt-1 +…+Yt-n+1)/n

Where:
Ft+1 = forecast for time period t+1
Yt = actual value in time period t n = number of periods to average
For ease in the computation, the Analysis Toolpak property in the Excel Software is utilized to find directly the values corresponding to each quarters.

C. Weighted Moving Average
Each of the observations used in this model is weighted equally, attaching more weight on observations that are closer to the time period being forecasted. This is usually used when a trend or other patterns is emerging. The formula is shown below.
Ft+1 = ∑ (Weight in period i) (Actual value in period)/ ∑ (Weights)

The two-quarter weighted moving average is used for this model since it provides the lowest MAD among the other periods. To calculate this, the product of each two weights as well as the arrival data for the past two months are added together divided by the sum of all the weights

D. Simple Exponential Smoothing
Type of moving average which fits a smoothing equation to data by minimizing the errors between actual data points and model estimates. It is easy to use but requires a lot of record keeping. This model is solved by:
Ft+1 =F(t) + α(Yt – Ft)

Where:
Ft+1= new forecast (for time period t+1)
F(t)= previous forecast (for time period t) α= smoothing constant (0< α<1)
Y(t)= previous period’s actual demand
A larger α gives more important to recent data while a smaller value gives more importance to past data. In the computation as presented in the appendices, the “best fitting α” is 0.1 since it got the lower MAD among other alphas. This is also done through the Analysis Toolpak property in Excel.

E. Linear Trend Projection
This model is good for those observations which exhibit a linear trend. It is a linear regression equation in which the independent variable (x) is the time period and the dependent variable is the actual observed value. It is computed by finding the equation of the line through this formula:
Y = b0 + b1X

Where:
Y= predicted value b0= intercept b1= slope of the line
X= time period

For the trend projection, instead of solving manually, the authors used the Excel to find the equation of the line. After finding the slope and intercept, the time period for the next four quarters are used to find the predicted production.

F. Decomposition Method with Trend and Seasonality
As cited in the earlier paragraphs, rice production in Iloilo city is seasonal, thus there is a need to deseasonalize or take on seasonal adjustments with reference to the trend line through the decomposition method. Decomposition method is highly-sophisticated and capable of finding multiple, subtle patterns.

Computation involves finding the seasonal indices by using the CMA or the centered moving average wherever possible. Dividing the actual production by the CMA results to a seasonal ratio. With this seasonal ratio, deseasonalized data can be directly acquired. These data are computed by dividing the actual production by the seasonal index. With these figures, a trend equation can be sought through the use of the Excel software, hence by substituting the succeeding four quarters in 2014 and multiplying it with the corresponding seasonal indices, prediction for the possible production are readily determined.

Excel Software has been really helpful in finding the forecasted figures on each model. The Analysis Toolpak property in the Data Analysis category is of so much use in computing for the moving average as well as the exponential smoothing. The trend projection line as well as the trend projection equation, on the other hand is directly defined through the use of the additional features in the chart elements of the selected charts and line graphs. Thus, over the duration of forecast and accuracy testing, Excel is of great benefit.

CHAPTER IV
PRESENTATION OF DATA

Different articles on rice production suggest that rice grains take approximately at least three months to a maximum of about six months, or one to two quarters to mature and be ready for harvest, depending on the type of rice being grown (Pitzer, 2009). Hence, it is but appropriate that the dependent variable to be forecasted in this study is the quarterly rice production in metric tons in the province of Iloilo. The independent variable of this study is the period of production which is every quarter of years 2004 to 2013.

Year | Quarter 1 | Quarter 2 | Quarter 3 | Quarter 4 | 2004 | 238,616.00 | 22,879.00 | 347,517.00 | 220,015.00 | 2005 | 209,951.00 | 29,007.00 | 177,879.00 | 253,463.00 | 2006 | 256,025.00 | 31,751.00 | 302,819.00 | 264,051.00 | 2007 | 190,795.00 | 32,259.00 | 315,184.00 | 285,138.00 | 2008 | 296,162.00 | 50,546.00 | 328,378.00 | 267,200.00 | 2009 | 272,580.00 | 65,161.00 | 404,560.00 | 201,749.00 | 2010 | 168,525.00 | 4,760.00 | 165,000.00 | 321,685.00 | 2011 | 325,883.00 | 50,400.00 | 379,704.00 | 203,252.00 | 2012 | 283,249.00 | 37,628.00 | 411,113.00 | 263,412.00 | 2013 | 204,618.00 | 22,194.00 | 304,513.00 | 291,127.00 | Table 2. | The actual quarterly and annual rice production in the Province of Iloilo (in metric tons) from 2004 to 2013 | As shown in the table above, rice production is at its lowest every second quarter of the year producing a range of only 4,000 to 70,000 metric tons. The rest of the quarters on the other hand, produce higher yields of rice, ranging from 100,000 to more than 400,000 metric tons. The minimum quarterly data point within the time frame is recorded during the second quarter of 2010 while the maximum quarterly data point is recorded during the third quarter of 2012. These data points are reflected in the figures below, presented in two different ways.

Figure 2. | The actual quarterly rice production in the Province of Iloilo (in metric tons) from 2004 to 2013 grouped per quarter. |

Figure 3. | The actual quarterly rice production in the Province of Iloilo (in metric tons) from 2004 to 2013. |

Figures two and three use the same data points, though presented differently. Figure two presents the quarterly rice production from 2004 to 2013, wherein the data points are grouped by quarter as reflected in four different lines labeled accordingly. Figure three, on the other hand, shows the actual fluctuations in the production of rice from quarter to quarter reflected in a single line. It depicts quarterly trends of rice production from 2004 to 2013 emphasizing a decreasing trend every second quarter and an increasing trend every third quarter.

CHAPTER V
FORECASTS AND ACCURACY TESTING

Period | Quarterly Rice ProductionUsing Different Forecasting Models | Year | Quarter | Actual Data | Naive | Simple Moving Ave. | Weighted Moving Ave. | Simple Exp. Smoothing | Trend Projection | Decomposition | 2004 | 1 | 238,616 | - | - | - | 205,981.75 | 190,259.53 | 198,229.74 | | 2 | 22,879 | 238,616 | - | - | 235,352.58 | 191,401.03 | 199,036.72 | | 3 | 347,517 | 22,879 | - | - | 44,126.36 | 192,542.52 | 199,843.70 | | 4 | 220,015 | 347,517 | - | - | 317,177.94 | 193,684.02 | 200,650.67 | 2005 | 1 | 209,951 | 220,015 | 207,256.75 | - | 229,731.29 | 194,825.51 | 201,457.65 | | 2 | 29,007 | 209,951 | 200,090.50 | - | 211,929.03 | 195,967.01 | 202,264.63 | | 3 | 177,879 | 29,007 | 201,622.50 | - | 47,299.20 | 197,108.51 | 203,071.60 | | 4 | 253,463 | 177,879 | 159,213.00 | - | 164,821.02 | 198,250.00 | 203,878.58 | 2006 | 1 | 256,025 | 253,463 | 167,575.00 | - | 244,598.80 | 199,391.50 | 204,685.56 | | 2 | 31,751 | 256,025 | 179,093.50 | - | 254,882.38 | 200,532.99 | 205,492.54 | | 3 | 302,819 | 31,751 | 179,779.50 | 169,552 | 54,064.14 | 201,674.49 | 206,299.51 | | 4 | 264,051 | 302,819 | 211,014.50 | 192,117 | 277,943.51 | 202,815.99 | 207,106.49 | 2007 | 1 | 190,795 | 264,051 | 213,661.50 | 206,467 | 265,440.25 | 203,957.48 | 207,913.47 | | 2 | 32,259 | 190,795 | 197,354.00 | 203,112 | 198,259.53 | 205,098.98 | 208,720.44 | | 3 | 315,184 | 32,259 | 197,481.00 | 173,781 | 48,859.05 | 206,240.47 | 209,527.42 | | 4 | 285,138 | 315,184 | 200,572.25 | 199,306 | 288,551.51 | 207,381.97 | 210,334.40 | 2008 | 1 | 296,162 | 285,138 | 205,844.00 | 217,454 | 285,479.35 | 208,523.46 | 211,141.38 | | 2 | 50,546 | 296,162 | 232,185.75 | 232,949 | 295,093.74 | 209,664.96 | 211,948.35 | | 3 | 328,378 | 50,546 | 236,757.50 | 201,637 | 75,000.77 | 210,806.46 | 212,755.33 | | 4 | 267,200 | 328,378 | 240,056.00 | 224,529 | 303,040.28 | 211,947.95 | 213,562.31 | 2009 | 1 | 272,580 | 267,200 | 235,571.50 | 234,982 | 270,784.03 | 213,089.45 | 214,369.28 | | 2 | 65,161 | 272,580 | 229,676.00 | 242,132 | 272,400.40 | 214,230.94 | 215,176.26 | | 3 | 404,560 | 65,161 | 233,329.75 | 212,120 | 85,884.94 | 215,372.44 | 215,983.24 | | 4 | 201,749 | 404,560 | 252,375.25 | 247,432 | 372,692.49 | 216,513.94 | 216,790.21 | 2010 | 1 | 168,525 | 201,749 | 236,012.50 | 241,984 | 218,843.35 | 217,655.43 | 217,597.19 | | 2 | 4,760 | 168,525 | 209,998.75 | 227,413 | 173,556.83 | 218,796.93 | 218,404.17 | | 3 | 165,000 | 4,760 | 194,898.50 | 185,733 | 21,639.68 | 219,938.42 | 219,211.15 | | 4 | 321,685 | 165,000 | 135,008.50 | 178,285 | 150,663.97 | 221,079.92 | 220,018.12 | 2011 | 1 | 325,883 | 321,685 | 164,992.50 | 201,710 | 304,582.90 | 222,221.41 | 220,825.10 | | 2 | 50,400 | 325,883 | 204,332.00 | 220,969 | 323,752.99 | 223,362.91 | 221,632.08 | | 3 | 379,704 | 50,400 | 215,742.00 | 190,185 | 77,735.30 | 224,504.41 | 222,439.05 | | 4 | 203,252 | 379,704 | 269,418.00 | 223,217 | 349,507.13 | 225,645.90 | 223,246.03 | 2012 | 1 | 283,249 | 203,252 | 239,809.75 | 222,219 | 217,877.51 | 226,787.40 | 224,053.01 | | 2 | 37,628 | 283,249 | 229,151.25 | 233,254 | 276,711.85 | 227,928.89 | 224,859.99 | | 3 | 411,113 | 37,628 | 225,958.25 | 201,838 | 61,536.39 | 229,070.39 | 225,666.96 | | 4 | 263,412 | 411,113 | 233,810.50 | 241,311 | 376,155.34 | 230,211.89 | 226,473.94 | 2013 | 1 | 204,618 | 263,412 | 248,850.50 | 249,519 | 274,686.33 | 231,353.38 | 227,280.92 | | 2 | 22,194 | 204,618 | 229,192.75 | 242,335 | 211,624.83 | 232,494.88 | 228,087.89 | | 3 | 304,513 | 22,194 | 225,334.25 | 197,626 | 41,137.08 | 233,636.37 | 228,894.87 | | 4 | 291,127 | 304,513 | 198,684.25 | 213,692 | 278,175.41 | 234,777.87 | 229,701.85 | Table 3. | Quarterly Rice Production (in metric tons) in the Province of Iloilo Using Different Forecasting Techniques from 2004 to 2013 |

Naive

Figure 4. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using the Naïve forecasting technique. |

4-quarter Simple Moving Average

Figure 5. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using the four-quarter period simple moving average forecasting technique. |

10-quarter Weighted Moving Average

Figure 6. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using the ten-quarter period Weighted Moving Average forecasting technique. |

Simple Exponential Smoothing

Figure 7. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using Simple Exponential Smoothing forecasting technique. | Trend Projection Figure 8. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using Trend Projection forecasting technique. |
Decomposition Method

Figure 9. | Actual and Forecasted Quarterly Rice Production in the Province of Iloilo (in metric tons) using Decomposition method. |

CHAPTER VI
SUMMARY/ IMPLICATIONS
The Philippine’s economy is largely dependent on agriculture. Of the approximately 73 million population in 1998, the agriculture sector employs more than 11 million people and about 26 percent of these are women. There are about 29 million people dependent on agriculture.In 1998, the total area planted to crops was 11.6 million hectares. Of these, 5.5 million hectares are devoted to rice and corn, 4.8 million hectares for major crops and 1.3 million hectares for other crops. However, with the growing population, urbanization and industrialization today, especially in the province of Iloilo where there has been a voluminous investments set to conquer the province’s serenity, the area devoted to crop production has been slowly declining which subsequently greatly affects the production. With this, a heightened call for doable strategies are pursued to mitigate this occurrence especially to rice which is the staple food for more than 90 million Filipinos.
Cropping patterns of palay/rice has changed with weather conditions, especially now that the so-called climate change starts to dominate the world. Peak harvest used to commence in August but now, it is from September to October, which also corresponds to the peak trading months, as exemplified by the Figure and Table 1. The lean supply quarter is the 2nd quarter from April-June where traders, or even consumers store enough supply from the first and second cropping to ensure supple during lean production months.
In all the forecasting methods utilized, although one can directly say that it’s the Decomposition Method that is the most accurate since it points out seasonality of production, which really holds true for rice, the computations show the other way. It is the Simple Exponential Smoothing that is accurate due to the fact that it brought up the lowest MAD in the solving, with an alpha of 0.9 which means that the most recent data have direct influence on the data set.
Moreover, it is also evident that with the aid of all the forecasting models, majority of them show that rice production in the province of Iloilo will have a slight decrease for the next forecasted quarter, Quarter 1 of 2014. From this information alone, it is high time that the province of Iloilo should not cease in devising ways to minimize this decrease. Extra effort is needed to develop technologies and strategies for optimizing farm productivity. The province could not afford to lose tie on this very major concern because this fluctuation, as what this paper has been continually reiterating, has significant impacts on food security, especially for the poorest people. Its stabilization is very much of critical concern for the province in terms of food security and the alleviation of property (Dawe et al. 2006, 2009).
Let this be a wake-up call for those who are in the position to recommend actions for this fluctuation. A rice diversification scheme must be implemented to address this issue; intensifying Agrarian Reform program and increasing annual budget for rice are among one of the steps to uplift the rice economy from its nearing downfall. Because, together, hand-in-hand, if the people of Iloilo are ready to take on this challenge on rice production, a more productive province will soar high.

REFERENCES

Blinkremz, (2014). PH Population to Reach 100 Million on the first month of 2014. Retrieved from http://philnews.ph/2014/01/06/ph-population-to-reach-100-million-on-the-first-month-of-2014/
Bureau of Agricultural Statistics. (2014). Palay and Corn: Volume of Production by Ecosystem/Croptype, by Quarter, by Semester, by Region and by Province [Data file]. Retrieved February 26, 2014, from http://countrystat.bas.gov.ph/selection.asp
CECAP, PhilRice and IIRR. (2000). "Highland Rice Production in the Philippine Cordillera."
___________."Factbox - Top 10 rice exporting, importing countries". Reuters. 28 January 2011. Retrieved 10 March 2014
___________.FAO Stat: Food and Agricultural Organization of the United Nations. Retrieved from http://faostat.fao.org/
French, Lilibeth A. (January 2014). Iloilo estimated to hit 1.950M population in 2014. Retrieved from http://r06.pia.gov.ph/index.php?article=931389691125.
Gumapac, Maria Anna M. (2012). Rice: A Filipino constant. Retrieved from http://www.bar.gov.ph/digest-home/digest-archives/364-2011-4th-quarter
___________. International Rice Research Institute (n.d.). Why does the Philippines import rice? Retrieved from: http://irri.org/news-events/hot-topics/why-does-the-philippines-import-rice

Levin, R., et al. (2001). Quantitative Approaches to Management (8th Ed.). McGraw-Hill Education (Asia)
Linares. (2002). African rice (Oryzaglaberrima): History and future potential. PNAS 99:16360-16365
___________. "Philippines: A Country Study:Rice and the Green Revolution". Library of Congress, Washington, D.C. June 1991. Retrieved March 10, 2014.
___________. Pinoy Rice Knowledge Bank (n.d.). Philippine rice industry: facts and figures. Retrieved from: http://pinoyrkb.com/main/resources/facts-and-figures
Pitzer, S. (2009). Growing Rice. Mother Earth News. Retrieved March 12, 2014, from http://www.motherearthnews.com/Organic-Gardening/Growing-Rice-How-To.aspx?PageId=2
___________(2012). Iloilo Included in Country's Top 10 Rice Producers List. Sun Star Iloilo. Retrieved March 11, 2014, from http://www.sunstar.com.ph/iloilo/local-news/2012/02/09/iloilo-included-countrys-top-10-rice-producers-list-205133
____________(2012). Iloilo’s Aromatic Rice Shows Export Potential. The Daily Guardian. Retrieved March 11, 2014, from http://www.thedailyguardian.net/index.php/local-news/20412-iloilos-aromatic-rice-shows-export-potential

APPENDICES

Appendix 1
Naïve Forecasting Year | Quarter | Actual(metric tons) | Forecasted(metric tons) | Error | 2004 | 1 | 238,616 | - | - | | 2 | 22,879 | 238,616 | -215,737 | | 3 | 347,517 | 22,879 | 324,638 | | 4 | 220,015 | 347,517 | -127,502 | 2005 | 1 | 209,951 | 220,015 | -10,064 | | 2 | 29,007 | 209,951 | -180,944 | | 3 | 177,879 | 29,007 | 148,872 | | 4 | 253,463 | 177,879 | 75,584 | 2006 | 1 | 256,025 | 253,463 | 2,562 | | 2 | 31,751 | 256,025 | -224,274 | | 3 | 302,819 | 31,751 | 271,068 | | 4 | 264,051 | 302,819 | -38,768 | 2007 | 1 | 190,795 | 264,051 | -73,256 | | 2 | 32,259 | 190,795 | -158,536 | | 3 | 315,184 | 32,259 | 282,925 | | 4 | 285,138 | 315,184 | -30,046 | 2008 | 1 | 296,162 | 285,138 | 11,024 | | 2 | 50,546 | 296,162 | -245,616 | | 3 | 328,378 | 50,546 | 277,832 | | 4 | 267,200 | 328,378 | -61,178 | 2009 | 1 | 272,580 | 267,200 | 5,380 | | 2 | 65,161 | 272,580 | -207,419 | | 3 | 404,560 | 65,161 | 339,399 | | 4 | 201,749 | 404,560 | -202,811 | 2010 | 1 | 168,525 | 201,749 | -33,224 | | 2 | 4,760 | 168,525 | -163,765 | | 3 | 165,000 | 4,760 | 160,240 | | 4 | 321,685 | 165,000 | 156,685 | 2011 | 1 | 325,883 | 321,685 | 4,198 | | 2 | 50,400 | 325,883 | -275,483 | | 3 | 379,704 | 50,400 | 329,304 | | 4 | 203,252 | 379,704 | -176,452 | 2012 | 1 | 283,249 | 203,252 | 79,997 | | 2 | 37,628 | 283,249 | -245,621 | | 3 | 411,113 | 37,628 | 373,485 | | 4 | 263,412 | 411,113 | -147,701 | 2013 | 1 | 204,618 | 263,412 | -58,794 | | 2 | 22,194 | 204,618 | -182,424 | | 3 | 304,513 | 22,194 | 282,319 | | 4 | 291,127 | 304,513 | -13,386 | | MAD | 158,936.23 | | | MSE | 37,043,314,470.18 | | | MAPE | 268.80% | | |

Appendix 2
Simple Moving Average Year | Quarter | Actual(metric tons) | Forecasted(metric tons) | Error | 2004 | 1 | 238,616 | - | - | | 2 | 22,879 | - | - | | 3 | 347,517 | - | - | | 4 | 220,015 | - | - | 2005 | 1 | 209,951 | 207,256.75 | 2694.25 | | 2 | 29,007 | 200,090.50 | -171083.50 | | 3 | 177,879 | 201,622.50 | -23743.50 | | 4 | 253,463 | 159,213.00 | 94250.00 | 2006 | 1 | 256,025 | 167,575.00 | 88450.00 | | 2 | 31,751 | 179,093.50 | -147342.50 | | 3 | 302,819 | 179,779.50 | 123039.50 | | 4 | 264,051 | 211,014.50 | 53036.50 | 2007 | 1 | 190,795 | 213,661.50 | -22866.50 | | 2 | 32,259 | 197,354.00 | -165095.00 | | 3 | 315,184 | 197,481.00 | 117703.00 | | 4 | 285,138 | 200,572.25 | 84565.75 | 2008 | 1 | 296,162 | 205,844.00 | 90318.00 | | 2 | 50,546 | 232,185.75 | -181639.75 | | 3 | 328,378 | 236,757.50 | 91620.50 | | 4 | 267,200 | 240,056.00 | 27144.00 | 2009 | 1 | 272,580 | 235,571.50 | 37008.50 | | 2 | 65,161 | 229,676.00 | -164515.00 | | 3 | 404,560 | 233,329.75 | 171230.25 | | 4 | 201,749 | 252,375.25 | -50626.25 | 2010 | 1 | 168,525 | 236,012.50 | -67487.50 | | 2 | 4,760 | 209,998.75 | -205238.75 | | 3 | 165,000 | 194,898.50 | -29898.50 | | 4 | 321,685 | 135,008.50 | 186676.50 | 2011 | 1 | 325,883 | 164,992.50 | 160890.50 | | 2 | 50,400 | 204,332.00 | -153932.00 | | 3 | 379,704 | 215,742.00 | 163962.00 | | 4 | 203,252 | 269,418.00 | -66166.00 | 2012 | 1 | 283,249 | 239,809.75 | 43439.25 | | 2 | 37,628 | 229,151.25 | -191523.25 | | 3 | 411,113 | 225,958.25 | 185154.75 | | 4 | 263,412 | 233,810.50 | 29601.50 | 2013 | 1 | 204,618 | 248,850.50 | -44232.50 | | 2 | 22,194 | 229,192.75 | -206998.75 | | 3 | 304,513 | 225,334.25 | 79178.75 | | 4 | 291,127 | 198,684.25 | 92442.75 | | MAD | 105,966.54167 | | | MSE | 15,061,126,235.60420 | | | MAPE | 250.12% | | |

Appendix 3
Weighted Moving Averages Year | Quarter | Actual(metric tons) | Forecasted(metric tons) | Error | 2004 | 1 | 238,616 | - | - | | 2 | 22,879 | - | - | | 3 | 347,517 | - | - | | 4 | 220,015 | - | - | 2005 | 1 | 209,951 | - | - | | 2 | 29,007 | - | - | | 3 | 177,879 | - | - | | 4 | 253,463 | - | - | 2006 | 1 | 256,025 | - | - | | 2 | 31,751 | - | - | | 3 | 302,819 | 169,552 | 133266.75 | | 4 | 264,051 | 192,117 | 71933.53 | 2007 | 1 | 190,795 | 206,467 | -15671.64 | | 2 | 32,259 | 203,112 | -170852.58 | | 3 | 315,184 | 173,781 | 141402.71 | | 4 | 285,138 | 199,306 | 85832.35 | 2008 | 1 | 296,162 | 217,454 | 78708.22 | | 2 | 50,546 | 232,949 | -182403.35 | | 3 | 328,378 | 201,637 | 126741.15 | | 4 | 267,200 | 224,529 | 42671.33 | 2009 | 1 | 272,580 | 234,982 | 37598.29 | | 2 | 65,161 | 242,132 | -176971.04 | | 3 | 404,560 | 212,120 | 192440.38 | | 4 | 201,749 | 247,432 | -45683.29 | 2010 | 1 | 168,525 | 241,984 | -73458.60 | | 2 | 4,760 | 227,413 | -222652.55 | | 3 | 165,000 | 185,733 | -20732.56 | | 4 | 321,685 | 178,285 | 143400.09 | 2011 | 1 | 325,883 | 201,710 | 124172.80 | | 2 | 50,400 | 220,969 | -170568.96 | | 3 | 379,704 | 190,185 | 189518.73 | | 4 | 203,252 | 223,217 | -19964.85 | 2012 | 1 | 283,249 | 222,219 | 61030.45 | | 2 | 37,628 | 233,254 | -195626.40 | | 3 | 411,113 | 201,838 | 209275.45 | | 4 | 263,412 | 241,311 | 22100.93 | 2013 | 1 | 204,618 | 249,519 | -44901.18 | | 2 | 22,194 | 242,335 | -240140.71 | | 3 | 304,513 | 197,626 | 106887.45 | | 4 | 291,127 | 213,692 | 77434.60 | | MAD | 114,135 | | | MSE | 17,637,049,555 | | | MAPE | 611% | | |

Appendix 4
Simple Exponential Smoothing Year | Quarter | Actual(metric tons) | Forecasted(metric tons) | Error | 2004 | 1 | 238,616 | 205,982 | 3,263.42 | | 2 | 22,879 | 235,352.58 | -21,247.36 | | 3 | 347,517 | 44,126.36 | 30,339.06 | | 4 | 220,015 | 317,177.94 | -9,716.29 | 2005 | 1 | 209,951 | 229,731.29 | -1,978.03 | | 2 | 29,007 | 211,929.03 | -18,292.20 | | 3 | 177,879 | 47,299.20 | 13,057.98 | | 4 | 253,463 | 164,821.02 | 8,864.20 | 2006 | 1 | 256,025 | 244,598.80 | 1,142.62 | | 2 | 31,751 | 254,882.38 | -22,313.14 | | 3 | 302,819 | 54,064.14 | 24,875.49 | | 4 | 264,051 | 277,943.51 | -1,389.25 | 2007 | 1 | 190,795 | 265,440.25 | -7,464.53 | | 2 | 32,259 | 198,259.53 | -16,600.05 | | 3 | 315,184 | 48,859.05 | 26,632.49 | | 4 | 285,138 | 288,551.51 | -341.35 | 2008 | 1 | 296,162 | 285,479.35 | 1,068.26 | | 2 | 50,546 | 295,093.74 | -24,454.77 | | 3 | 328,378 | 75,000.77 | 25,337.72 | | 4 | 267,200 | 303,040.28 | -3,584.03 | 2009 | 1 | 272,580 | 270,784.03 | 179.60 | | 2 | 65,161 | 272,400.40 | -20,723.94 | | 3 | 404,560 | 85,884.94 | 31,867.51 | | 4 | 201,749 | 372,692.49 | -17,094.35 | 2010 | 1 | 168,525 | 218,843.35 | -5,031.83 | | 2 | 4,760 | 173,556.83 | -16,879.68 | | 3 | 165,000 | 21,639.68 | 14,336.03 | | 4 | 321,685 | 150,663.97 | 17,102.10 | 2011 | 1 | 325,883 | 304,582.90 | 2,130.01 | | 2 | 50,400 | 323,752.99 | -27,335.30 | | 3 | 379,704 | 77,735.30 | 30,196.87 | | 4 | 203,252 | 349,507.13 | -14,625.51 | 2012 | 1 | 283,249 | 217,877.51 | 6,537.15 | | 2 | 37,628 | 276,711.85 | -23,908.39 | | 3 | 411,113 | 61,536.39 | 34,957.66 | | 4 | 263,412 | 376,155.34 | -11,274.33 | 2013 | 1 | 204,618 | 274,686.33 | -7,006.83 | | 2 | 22,194 | 211,624.83 | -18,943.08 | | 3 | 304,513 | 41,137.08 | 26,337.59 | | 4 | 291,127 | 278,175.41 | 291,127.00 | | MAD | 21,988.93 | | | MSE | 2,443,055,880.58 | | | MAPE | 28.73% | | |

Appendix 5
Trend Projection Year | Quarter | Actual | Forecasted | Error | 2004 | 1 | 238,616 | 190,259.53 | 48,356.47 | | 2 | 22,879 | 191,401.03 | -168,522.03 | | 3 | 347,517 | 192,542.52 | 154,974.48 | | 4 | 220,015 | 193,684.02 | 26,330.98 | 2005 | 1 | 209,951 | 194,825.51 | 15,125.49 | | 2 | 29,007 | 195,967.01 | -166,960.01 | | 3 | 177,879 | 197,108.51 | -19,229.51 | | 4 | 253,463 | 198,250.00 | 55,213.00 | 2006 | 1 | 256,025 | 199,391.50 | 56,633.50 | | 2 | 31,751 | 200,532.99 | -168,781.99 | | 3 | 302,819 | 201,674.49 | 101,144.51 | | 4 | 264,051 | 202,815.99 | 61,235.01 | 2007 | 1 | 190,795 | 203,957.48 | -13,162.48 | | 2 | 32,259 | 205,098.98 | -172,839.98 | | 3 | 315,184 | 206,240.47 | 108,943.53 | | 4 | 285,138 | 207,381.97 | 77,756.03 | 2008 | 1 | 296,162 | 208,523.46 | 87,638.54 | | 2 | 50,546 | 209,664.96 | -159,118.96 | | 3 | 328,378 | 210,806.46 | 117,571.54 | | 4 | 267,200 | 211,947.95 | 55,252.05 | 2009 | 1 | 272,580 | 213,089.45 | 59,490.55 | | 2 | 65,161 | 214,230.94 | -149,069.94 | | 3 | 404,560 | 215,372.44 | 189,187.56 | | 4 | 201,749 | 216,513.94 | -14,764.94 | 2010 | 1 | 168,525 | 217,655.43 | -49,130.43 | | 2 | 4,760 | 218,796.93 | -214,036.93 | | 3 | 165,000 | 219,938.42 | -54,938.42 | | 4 | 321,685 | 221,079.92 | 100,605.08 | 2011 | 1 | 325,883 | 222,221.41 | 103,661.59 | | 2 | 50,400 | 223,362.91 | -172,962.91 | | 3 | 379,704 | 224,504.41 | 155,199.59 | | 4 | 203,252 | 225,645.90 | -22,393.90 | 2012 | 1 | 283,249 | 226,787.40 | 56,461.60 | | 2 | 37,628 | 227,928.89 | -190,300.89 | | 3 | 411,113 | 229,070.39 | 182,042.61 | | 4 | 263,412 | 230,211.89 | 33,200.11 | 2013 | 1 | 204,618 | 231,353.38 | -26,735.38 | | 2 | 22,194 | 232,494.88 | -210,300.88 | | 3 | 304,513 | 233,636.37 | 70,876.63 | | 4 | 291,127 | 234,777.87 | 56,349.13 | | | | | 48,356.47 | slope | 1141.495872 | Y=189118.03 + 1141.50X | intercept | 189118.0346 | | | | MAD | 98,662.48 | | | | MSE | 13,641,326,447.30 | | | | MAPE | 248.803785% | | | |

Appendix 6
Decomposition Method Year | Quarter | Actual (Y) | CMA | Seasonal Ratio | Seasonal Index | Deseasonalized Production | X | XY | X^2 | 2004 | 1 | 238,616 | - | - | 1.15107 | 207,299.69696 | 1 | 207,299.70 | 1 | | 2 | 22,879 | - | - | 0.16229 | 140,978.71400 | 2 | 281,957.43 | 4 | | 3 | 347,517 | 203,673.63 | 1.70624 | 1.45596 | 238,685.12774 | 3 | 716,055.38 | 9 | | 4 | 220,015 | 200,856.50 | 1.09538 | 1.19957 | 183,411.85486 | 4 | 733,647.42 | 16 | 2005 | 1 | 209,951 | 180,417.75 | 1.16369 | 1.15107 | 182,396.37902 | 5 | 911,981.90 | 25 | | 2 | 29,007 | 163,394.00 | 0.17753 | 0.16229 | 178,735.59677 | 6 | 1,072,413.58 | 36 | | 3 | 177,879 | 173,334.25 | 1.02622 | 1.45596 | 122,172.99926 | 7 | 855,210.99 | 49 | | 4 | 253,463 | 179,436.50 | 1.41255 | 1.19957 | 211,294.88067 | 8 | 1,690,359.05 | 64 | 2006 | 1 | 256,025 | 195,397.00 | 1.31028 | 1.15107 | 222,423.48424 | 9 | 2,001,811.36 | 81 | | 2 | 31,751 | 212,338.00 | 0.14953 | 0.16229 | 195,643.60096 | 10 | 1,956,436.01 | 100 | | 3 | 302,819 | 205,507.75 | 1.47352 | 1.45596 | 207,985.79631 | 11 | 2,287,843.76 | 121 | | 4 | 264,051 | 197,417.50 | 1.33753 | 1.19957 | 220,121.37683 | 12 | 2,641,456.52 | 144 | 2007 | 1 | 190,795 | 199,026.63 | 0.95864 | 1.15107 | 165,754.47193 | 13 | 2,154,808.14 | 169 | | 2 | 32,259 | 203,208.13 | 0.15875 | 0.16229 | 198,773.79999 | 14 | 2,782,833.20 | 196 | | 3 | 315,184 | 219,014.88 | 1.43910 | 1.45596 | 216,478.47468 | 15 | 3,247,177.12 | 225 | | 4 | 285,138 | 234,471.63 | 1.21609 | 1.19957 | 237,700.17590 | 16 | 3,803,202.81 | 256 | 2008 | 1 | 296,162 | 238,406.75 | 1.24226 | 1.15107 | 257,292.77976 | 17 | 4,373,977.26 | 289 | | 2 | 50,546 | 237,813.75 | 0.21254 | 0.16229 | 311,454.80313 | 18 | 5,606,186.46 | 324 | | 3 | 328,378 | 232,623.75 | 1.41163 | 1.45596 | 225,540.53683 | 19 | 4,285,270.20 | 361 | | 4 | 267,200 | 231,502.88 | 1.15420 | 1.19957 | 222,746.48416 | 20 | 4,454,929.68 | 400 | 2009 | 1 | 272,580 | 242,852.50 | 1.12241 | 1.15107 | 236,805.75465 | 21 | 4,972,920.85 | 441 | | 2 | 65,161 | 244,193.88 | 0.26684 | 0.16229 | 401,509.64323 | 22 | 8,833,212.15 | 484 | | 3 | 404,560 | 223,005.63 | 1.81412 | 1.45596 | 277,864.77650 | 23 | 6,390,889.86 | 529 | | 4 | 201,749 | 202,448.63 | 0.99654 | 1.19957 | 168,184.43276 | 24 | 4,036,426.39 | 576 | 2010 | 1 | 168,525 | 164,953.50 | 1.02165 | 1.15107 | 146,407.25586 | 25 | 3,660,181.40 | 625 | | 2 | 4,760 | 150,000.50 | 0.03173 | 0.16229 | 29,330.21135 | 26 | 762,585.50 | 676 | | 3 | 165,000 | 184,662.25 | 0.89352 | 1.45596 | 113,327.28921 | 27 | 3,059,836.81 | 729 | | 4 | 321,685 | 210,037.00 | 1.53156 | 1.19957 | 268,166.92648 | 28 | 7,508,673.94 | 784 | 2011 | 1 | 325,883 | 242,580.00 | 1.34340 | 1.15107 | 283,113.10346 | 29 | 8,210,280.00 | 841 | | 2 | 50,400 | 254,613.88 | 0.19795 | 0.16229 | 310,555.17900 | 30 | 9,316,655.37 | 900 | | 3 | 379,704 | 234,480.50 | 1.61934 | 1.45596 | 260,792.87893 | 31 | 8,084,579.25 | 961 | | 4 | 203,252 | 227,554.75 | 0.89320 | 1.19957 | 169,437.38173 | 32 | 5,421,996.22 | 1024 | 2012 | 1 | 283,249 | 229,884.38 | 1.23214 | 1.15107 | 246,074.52197 | 33 | 8,120,459.22 | 1089 | | 2 | 37,628 | 241,330.50 | 0.15592 | 0.16229 | 231,856.55308 | 34 | 7,883,122.80 | 1156 | | 3 | 411,113 | 239,021.63 | 1.71998 | 1.45596 | 282,365.58697 | 35 | 9,882,795.54 | 1225 | | 4 | 263,412 | 227,263.50 | 1.15906 | 1.19957 | 219,588.68595 | 36 | 7,905,192.69 | 1296 | 2013 | 1 | 204,618 | 212,009.25 | 0.96514 | 1.15107 | 177,763.29850 | 37 | 6,577,242.04 | 1369 | | 2 | 22,194 | 202,148.63 | 0.10979 | 0.16229 | 136,755.19132 | 38 | 5,196,697.27 | 1444 | | 3 | 304,513 | - | - | 1.45596 | 209,149.28982 | 39 | 8,156,822.30 | 1521 | | 4 | 291,127 | - | - | 1.19957 | 242,692.79825 | 40 | 9,707,711.93 | 1600 | total | | 8,500,748 | | | | | 820 | 180,349,507.00 | 22140 | Ave. | | 212518.7 | | | | | 20.5 | | | | | | | | | | | | | slope | 806.9 | y = 806.9x + 197423 | | | | | | intercept | 197423 | | | | | | | |

Year | Quarter | Actual (Y) | Forecasted | Error | 2004 | 1 | 238,616 | 198,229.74 | 40,386.26 | | 2 | 22,879 | 199,036.72 | -176,157.72 | | 3 | 347,517 | 199,843.70 | 147,673.30 | | 4 | 220,015 | 200,650.67 | 19,364.33 | 2005 | 1 | 209,951 | 201,457.65 | 8,493.35 | | 2 | 29,007 | 202,264.63 | -173,257.63 | | 3 | 177,879 | 203,071.60 | -25,192.60 | | 4 | 253,463 | 203,878.58 | 49,584.42 | 2006 | 1 | 256,025 | 204,685.56 | 51,339.44 | | 2 | 31,751 | 205,492.54 | -173,741.54 | | 3 | 302,819 | 206,299.51 | 96,519.49 | | 4 | 264,051 | 207,106.49 | 56,944.51 | 2007 | 1 | 190,795 | 207,913.47 | -17,118.47 | | 2 | 32,259 | 208,720.44 | -176,461.44 | | 3 | 315,184 | 209,527.42 | 105,656.58 | | 4 | 285,138 | 210,334.40 | 74,803.60 | 2008 | 1 | 296,162 | 211,141.38 | 85,020.62 | | 2 | 50,546 | 211,948.35 | -161,402.35 | | 3 | 328,378 | 212,755.33 | 115,622.67 | | 4 | 267,200 | 213,562.31 | 53,637.69 | 2009 | 1 | 272,580 | 214,369.28 | 58,210.72 | | 2 | 65,161 | 215,176.26 | -150,015.26 | | 3 | 404,560 | 215,983.24 | 188,576.76 | | 4 | 201,749 | 216,790.21 | -15,041.21 | 2010 | 1 | 168,525 | 217,597.19 | -49,072.19 | | 2 | 4,760 | 218,404.17 | -213,644.17 | | 3 | 165,000 | 219,211.15 | -54,211.15 | | 4 | 321,685 | 220,018.12 | 101,666.88 | 2011 | 1 | 325,883 | 220,825.10 | 105,057.90 | | 2 | 50,400 | 221,632.08 | -171,232.08 | | 3 | 379,704 | 222,439.05 | 157,264.95 | | 4 | 203,252 | 223,246.03 | -19,994.03 | 2012 | 1 | 283,249 | 224,053.01 | 59,195.99 | | 2 | 37,628 | 224,859.99 | -187,231.99 | | 3 | 411,113 | 225,666.96 | 185,446.04 | | 4 | 263,412 | 226,473.94 | 36,938.06 | 2013 | 1 | 204,618 | 227,280.92 | -22,662.92 | | 2 | 22,194 | 228,087.89 | -205,893.89 | | 3 | 304,513 | 228,894.87 | 75,618.13 | | 4 | 291,127 | 229,701.85 | 61,425.15 | | | | | | MAD | 44,839.18 | | | | MSE | 3,884,398,332.55 | | | | MAPE | 120.46% | | | | | | | | |

Appendix 7
Simple Moving Average | MAD | MSE | MAPE | 2-quarter period | 136,149.80 | 24,760,895,772.27 | 255.98% | 3-quarter period | 127,231 | 23,207,848,269 | 23495.06% | 4-quarter period | 105,966.54167 | 15,061,126,235.60420 | 250.12% | 5-quarter period | 111,817.65 | 19,194,227,259.70 | 325.89 % | 6-quarter period | 109,698.67 | 16,819,575,588.55 | 265.49% | 10-quarter period | 112,688 | 16,994,319,638 | 620.03% |

Appendix 8
Weighted Moving Average | MAD | MSE | MAPE | 3-quarter period | 1,056,447 | 1,284,862,346,960 | 3664% | 4-quarter period | 120,400.56 | 19,877,437,555.94 | 273.53% | 5-quarter period | 118,925.24 | 19,227,623,655.48 | 276.98% | 6-quarter period | 114,476.96 | 17,093,548,655.40 | 250.91% | 10-quarter period | 114,135 | 17,637,049,555 | 611% |

Appendix 9
Simple Exponential Smoothing | MAD | MSE | MAPE | α= 0.1 | 103,667.13 | 15,131,175,792.11 | 252.2976207 | α= 0.2 | 108,021.63 | 16,605,316,348.75 | 260.0874139 | α= 0.3 | 113,105.78 | 18,238,631,193.38 | 264.1806726 | α= 0.4 | 118,787.31 | 20,038,877,662.96 | 266.6018629 | α= 0.5 | 124,983.34 | 22,019,292,463.81 | 267.859246 | α= 0.6 | 130,751.13 | 24,198,171,928.99 | 267.7535308 | α= 0.7 | 135,985.07 | 26,608,283,724.21 | 266.3802543 | α= 0.8 | 141,404.44 | 29,311,600,704.67 | 264.3361489 | α= 0.9 | 21,988.93 | 2,443,055,880.58 | 28.73367724 |…...

Similar Documents

Premium Essay

Forecasting Model

...in the future, so it should be based on forecasts of future conditions. Forecasts are needed throughout an organization -- and they should certainly not be produced by an isolated group of forecasters. Neither is forecasting ever "finished". Forecasts are needed continually, and as time moves on, the impact of the forecasts on actual performance is measured; original forecasts are updated; and decisions are modified, and so on. For example, many inventory systems cater for uncertain demand. The inventory parameters in these systems require estimates of the demand and forecast error distributions. The two stages of these systems, forecasting and inventory control, are often examined independently. Most studies tend to look at demand forecasting as if this were an end in itself, or at stock control models as if there were no preceding stages of computation. Nevertheless, it is important to understand the interaction between demand forecasting and inventory control since this influences the performance of the inventory system. This integrated process is shown in the following figure: The decision-maker uses forecasting models to assist him or her in decision-making process. The decision-making often uses the modeling process to investigate the impact of different courses of action retrospectively; that is, "as if" the decision has already been made under a course of action. That is why the sequence of steps in the modeling process, in the above figure must be considered......

Words: 573 - Pages: 3

Free Essay

Forecasting Models

.... . . . . . . . . . . . . . . . . . . . . . . Graph Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Graph Components . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Figure Tools . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Arranging Graphs Within a Figure . . . . . . . . . . . . . . . . . . . 3-2 3-2 3-3 3-3 3-7 3-7 3-8 3-15 vi Contents Choosing a Graph Type . . . . . . . . . . . . . . . . . . . . . . . . . . . . Choosing a Type of Graph to Plot . . . . . . . . . . . . . . . . . . . . . Editing Plots . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Plot Edit Mode . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Using Functions to Edit Graphs . . . . . . . . . . . . . . . . . . . . . . Interactive Plotting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Plotting Two Variables with Plotting Tools . . . . . . . . . . . . . Changing the Appearance of Lines and Markers . . . . . . . . Adding More Data to the Graph . . . . . . . . . . . . . . . . . . . . . . Changing the Type of Graph . . . . . . . . . . . . . . . . . . . . . . . . Modifying the Graph Data Source . . . . . . . . . . . . . . . . . . . . Preparing Graphs for Presentation . . . . . . . . . . . . . . . . . Annotating Graphs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Printing the Graph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Exporting...

Words: 36443 - Pages: 146

Free Essay

Forecasting Model in Use

...BU3315 Unit 4 Research Paper 2 Forecasting Model in Use For this research paper I used a study done by Sprint for forecasting usage costs and computer capacity required for their network and cell phone towers. The use of data related to transactions collected from computing devices in their facilities was used to calculate a forecast of usage at peak hours. This study was done in the early stages of Sprint becoming a cell phone company and it is still used today to help upgrade and maintain their network. This helped Sprint determine a forecast of data usage on customer cell phones so they could determine the type and amount of equipment needed to get ample coverage and network bandwidth to provide their cell phone service to the customers. The methods they used were 5 variables used in their forecasting model; 1. First span of time comprises usage in seconds, minutes, hours, days, months and years. 2. Computing device comprises at least one of a server, telecommunications switch and computer 3. Data collection of computing software processes, computer programs used, business logic model, and software usage (apps) 4. Software usage at server farms 5. Threshold percentage representing actual customer airtime usage By doing this Sprint was able to determine the demand that customers would be putting on their networks and the bandwidth being used. The first inclination was to build a massive network of coverage all across America to stake claim......

Words: 363 - Pages: 2

Premium Essay

Forecasting

...TOPIC 1. FUNDAMENTALS OF ECONOMIC FORECASTING TOPIC I TOPIC I. FUNDAMENTALS OF ECONOMIC FORECASTING   Contents 1. Meaning of forecasting 2. Features, importance and limitations of forecasting 3. Forecast types   1. Meaning of forecasting Forecast is a likely, scientifically well-grounded opinion about the possible state of the events, objects or processes in the future. Forecasting is a process of making statements about events whose actual outcomes (typically) have not yet been observed. Forecasting is a process of predicting or estimating the future based on past and present data. Economic Forecasting is a process of making forecasts based on analysis of past trends and regularities of the economic processes. Economic forecasts can be carried out at a high level of aggregation – for example for GDP, inflation, unemployment or the fiscal deficit – or at a more disaggregated level, for specific sectors of the economy or even specific companies. Economic forecasting provides information about the potential future events and their consequences for the organization. It may not reduce the complications and uncertainty of the future. However, it increases the confidence of the management to make important decisions.   Economic forecasting includes the following steps: 1. Identifying items to be forecast. The items of socio-economic forecasting are the economic processes (for example, inflation, demand, supply), any indicator describing the company activity (for......

Words: 17426 - Pages: 70

Premium Essay

Forecasting

...FORECASTING FUNDAMENTALS Forecast: A prediction, projection, or estimate of some future activity, event, or occurrence. Types of Forecasts * Economic forecasts * Predict a variety of economic indicators, like money supply, inflation rates, interest rates, etc. * Technological forecasts * Predict rates of technological progress and innovation. * Demand forecasts * Predict the future demand for a company’s products or services. Since virtually all the operations management decisions (in both the strategic category and the tactical category) require as input a good estimate of future demand, this is the type of forecasting that is emphasized in our textbook and in this course. TYPES OF FORECASTING METHODS Qualitative methods: These types of forecasting methods are based on judgments, opinions, intuition, emotions, or personal experiences and are subjective in nature. They do not rely on any rigorous mathematical computations. Quantitative methods: These types of forecasting methods are based on mathematical (quantitative) models, and are objective in nature. They rely heavily on mathematical computations. QUALITATIVE FORECASTING METHODS Qualitative Methods ...

Words: 8098 - Pages: 33

Premium Essay

Forecasting

...companies on a daily basis. Forecasting allows managers to plan according to future events and be prepared to use the system accordingly. With a prediction of the future managers reduce uncertainty and develop plans. The historical data is put together and analyzed to determine forecast events. All large companies use forecasting to make important strategic business decision. This helps them save costs and manage their resources effectively. A firm that is prepared for future occurences will have a healthy financial position. Forecast is of great use to a company because it affects several departments throughout the company. Some of the departments affected are: accounting and finance, marketing, operations, human resources, and information systems. Budgeting, sales, production, inventory control, capacity planning, and purchasing make use of forecasting. Accounting and finance use the data collected to estimate future costs, predict profit or loss, and identify resources available. The marketing department uses forecasting to predict prices and create promotions. The operations of a company is able to run smoothly because job schedules, production schedules, capacity planning, inventory planning, and detecting outsourcing needs are predicted ahead of time. Human resources also benefits from forecasting because seasonal or cyclical hiring is scheduled ahead of time. The company’s information systems are being monitored and revised to keep up with the forecasting results.......

Words: 551 - Pages: 3

Premium Essay

Forecasting Model

...The business development of the construction industry depends not only on the ability to optimize operations within industry, adapt to external conditions, but also on the country's economic development, the situation in the market. The Manpower forecasting model. The Estimated Manpower Forecast Model is designed to capture the future labour requirements of the engineering construction industry by key sectors. Manpower is undoubtedly a valuable asset upon which the construction industry depends. However, rapid changes of the economy, working arrangements, and technology in construction advocate reliable estimations of manpower demand to lessen future skills imbalance. The aim of this research is to develop advanced manpower demand forecasting models, at both project and industry levels, to facilitate manpower planning for the construction industry. At the project level, statistical models for forecasting the demand of labour demand for a construction project were developed using multiple regression analysis. Results reveal that project cost and project type play an important role in determining the project labour requirements. The forecasting models could serve as practical tools for contractors and government to predict the labour requirements and number of jobs created at an early outset, thus enabling proper human resources planning and budgeting. At the industry level, co-integration analysis was applied to develop a long-term relationship between aggregate......

Words: 390 - Pages: 2

Free Essay

Forecasting

...units. d. Develop a trend line for the demand for fertilizer using any computer software. e. You have now developed three different forecasts. These are a 3-year moving average, a weighted moving average, and a trend line. Which one would you use? Explain your answer. By observing the MAD in part (d), it can be observed that the value is the smallest among the 3 methods, hence I will choose the trend line as the forecast predicted is more accurate. Moreover the demand for the future can also be seen. 3-2 Sales of Cool-Man air conditioners have grown steadily during the past 5 years: Year Sales 1 440 2 465 3 520 4 573 5 586 6 ? The sales manager had predicted, before the business started, that year 1’s sales would be 410 air conditioners. a. Using exponential smoothing with a weights of a = 0.30, 0.60, and 0.90 develop forecasts for years 2 through 6. b. What effect did the smoothing constant have on the forecasts for Cool-Man air conditioners? As the smoothing constant move towards 1, the MAD between the data and forecast decreases enhancing the accuracy of the forecast predicted from 74.014 (a = 0.30), to 52.618 (a = 0.60), to 38.692 (a = 0.90). c. Which smoothing constant gives the most accurate forecast? By utilizing the smoothing constant of .90, it provides the most accurate forecast. d. Use a three-year moving average forecasting model to forecast the sales of Cool-Man air conditioners. e. Use......

Words: 837 - Pages: 4

Premium Essay

Forecasting

...FORECASTING - a method for translating past experience into estimates of the future. Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. A commonplace example might be estimation of the expected value for some variable of interest at some specified future date. Prediction is a similar, but more general term. Both might refer to formal statistical methods employing time series, cross-sectional or longitudinal data, or alternatively to less formal judgemental methods. Usage can differ between areas of application: for example in hydrology, the terms "forecast" and "forecasting" are sometimes reserved for estimates of values at certain specific future times, while the term "prediction" is used for more general estimates, such as the number of times floods will occur over a long period. Risk and uncertainty are central to forecasting and prediction; it is generally considered good practice to indicate the degree of uncertainty attaching to forecasts. The process of climate change and increasing energy prices has led to the usage of Egain Forecasting of buildings. The method uses Forecasting to reduce the energy needed to heat the building, thus reducing the emission of greenhouse gases. Forecasting is used in the practice of Customer Demand Planning in every day business forecasting for manufacturing companies. The discipline of demand planning, also sometimes referred to as supply chain forecasting, embraces...

Words: 3665 - Pages: 15

Premium Essay

Forecasting Production Demand

...The Importance of Accurate Demand Forecasting An Analysis of VMU America Inc. Christopher Chun & William McMahan Oakland University Abstract Most strategic business decisions, such as financial planning and production management, rely heavily on forecasts that attempt to paint an accurate picture of the future periods. Ineffective forecasting can lead businesses to improper conclusions about the environment in which they operate. The purpose of this research is to analyze the effectiveness of VMU Power Systems’ forecasting methods on production demand. Once the type/s of forecasting used is identified, a closer look highlights the fact that improvements to their methods could put the company in a better position to handle their current market demand. The underlying issue is that they are not including all of their products & services in their data set, or more simply put, they are basing their decisions off of incomplete data. This is causing their forecasted results to be far below the actual demand resulting in a lack of resources to produce at the levels required. Other research has been cited throughout this paper to further support the claims that it is possible for VMU to forecast their type of intermittent demand. There are two main recommendations made at the end of this analysis that, if implemented, could improve the accuracy of their models. The first suggestion is to use the SBA forecasting method on their after-sales demand. The second......

Words: 2776 - Pages: 12

Premium Essay

A Time Series Forecasting Analysis on the Monthly Stocks of Rice in the Philippines

...A Time Series Forecasting Analysis on the Monthly Stocks of Rice in the Philippines A Research Paper Presented To Dr. Cesar Rufino Of the Department of Economics School of Economics De La Salle University, Manila In Partial Fulfillment of the Course Requirements in Economic Forecasting (ECOFORE) Term 3 AY 2014-2015 Submitted by: Jayme, Kevin Matthew D. April 24 2015 0 I. Introduction The Philippines has been the accredited as an agricultural nation that provides different types of agricultural related goods, both for the domestic and international market. Rice has been the staple food in the Philippine to 80% of the population as it is customary diet that has been in beaded in the Philippine culture (Drilon Jr., 2012). Despite the strong history of agriculture and the skills and weather condition perfect for growth of rice, decrease of land and increase of total population around the Philippines decrease the opportunity for the population to have access to rice. In addition, neighboring countries, such as Thailand and Vietnam, had been on the rise of rice exportation. Not to mention the implementation of the ASEAN integration is happening in 2015. This means that the Philippines is lagging behind as it is the 8th largest exporters of rice in the world (Tiongco & Francisco, 2011). Institution, such as International Rice Research Institute (IRRI), has gone into research and development of rice growth in different conditions and......

Words: 2806 - Pages: 12

Premium Essay

Forecasting

...Forecasting is described as, “the art and science of predicting future events” (Heizer, Render, & Griffen, 2014). It’s used a planning tool that helps management cope with the uncertainty of the future. Forecasting has many purposes within businesses and the purpose will vary depending on what type of organization you’re running or working for. Forecasting includes many different types of techniques that have the ability to give detailed information about future measurements, challenges of future events, and the changes in the environment. It can also analyze present data and effective planning in both the short run and the long run fully depends on the forecasts established for the company’s products. Forecasting gives confidence in those making important decisions due to the relevant and reliable information predicted. Forecasting may involve the use of historical data through mathematical equations to track future trends, which is known as quantitative forecasts. Quantitative methods of forecasting falls into two categories, the Time Series Models such as Naïve Approach, Moving Averages and Exponential Smoothing as well as the Associative Model that includes Trend Projection and Linear Regression. Forecasting may also be used in a more subjective or intuitive prediction if historical data is not present, which is known as qualitative forecasts. This category of forecasting involves four specific techniques used, Jury of executive opinion, Delphi Method, Sales Force......

Words: 832 - Pages: 4

Free Essay

Powerplant Design in Iloilo Province

...Technology and Siting, and Powerplant Design in the Province of Iloilo Design Paper by Gino P. Jardinico BS Mechanical Engineering Student: 2011-15731 Submitted to the Department of Mechanical Engineering College of Engineering University of the Philippines In Partial Fulfilment of the Requirements of ME 188 Power Plant Engineering Department of Mechanical Engineering College of Engineering University of the Philippines Diliman Quezon City December 2015 ii Abstract The study is aimed (1) to quantify the demand for fuel requirements and powerplant capacity in the province of Iloilo for the next 30 years, and (2) prioritize the energy sources, conversion technologies and powerplant sites available in the province. Electricity consumption from the five sectors (residential, commercial, transportation, industrial, and agricultural) were calculated using different models and assumptions. These values were projected to the year 2045 in order to predict the total electricity demand on the daily, weekly, monthly and yearly bases. There is an average of 262.28 MW demand from the computed consumptions which was translated to fuel requirements considering the existing, upcoming, decommissioning, and the reserve. A total of 284.77 MW plant capacity was calculated for 2045. Assuming that bituminous coal will be used as the main fuel for running a Coal-fired powerplant in the future, a fuel requirement of 12.25 kg/s was obtained. From the different types of the considered fuel......

Words: 16888 - Pages: 68

Premium Essay

Forecasting Using Indices

...Forecasting Using Indices Tricia Thedford QRB 501/Quantitative Reasoning for Business March 4, 2012 Vinata Kulkarni, PhD Forecasting using indices Forecasting is an integral part of business. Forecasting allows investors to see anticipated growth/decline in a business. An accurate forecast will also allow a business to respond appropriately should a problem be evident in the desired business plan. Forecasting can be done on all data within a financial statement or can target specific areas, depending on the information desired. Investors as well as business executives have a need to see where a company is headed when making future business decisions. The dictionary defines the word forecast as “to anticipate, calculate, or predict (some future event or condition) usually as a result of rational study and analysis of available pertinent data” (Merriam-Webster, Inc., 2002, para 2). One should review all data available for making an accurate business forecast. In researching Dell, Inc., inventory history the following data was obtained: Dell, Inc. historical inventories data | 2011 | 2010 | Period | Amount | Period | Amount | October 31 | 1.40 billion | October 31 | 1.29 billion | July 31 | 1.35 billion | July 31 | 1.37 billion | April 30 | 1.28 billion | April 30 | 1.18 billion | January 31 | 1.30 billion | January 31 | 1.05 billion | 2009 | 2008 | Period | Amount | Period | Amount | October 31 | 952 million | October 31 | 1.11 billion | July...

Words: 592 - Pages: 3

Premium Essay

Forecasting -

...What is Forecasting? Forecasting is the process of making statements about events whose actual outcomes have not yet been observed. Forecasting can be seen as a planning tool for managers to attempt to cope with the uncertainty of the future. Managers are constantly trying to predict the future, making decisions in the present that will ensure the continued success of their firms. Managers use forecasts for budgeting purposes. A forecast aids in determining volume of production, inventory needs, labor hours required, cash requirements, and financing needs. A variety of forecasting methods are available. However, consideration has to be given to cost, preparation time, accuracy, and time period. The manager must understand clearly the assumptions on which a particular forecast method is based to obtain maximum benefit. 1 Types of Forecasts Short Term Short-range forecasts typically encompass the immediate future and concern the day to day operations of a firm. A short-term forecast usually only covers a period of a few months and can be considered an “operating” forecast. Medium Term Medium-range forecasts typically span a few months up to a year. A forecast of this length can be considered “tactical” in nature. Long Term Long-range forecasts typically encompass a period longer than 1 to 2 years. These forecasts are considered strategic and are generally related to management’s attempt to plan new products or build new facilities. 2 Forecasting Methods Time......

Words: 630 - Pages: 3