# Forecasting

FORECASTING

Casestudy 1

Revenue

SouthwesternUniversity football game Attendance

Question1

model

Theforecasting technique applied, in this case, is the quantitativemethod. I have forecasted the expected revenue of the year 2014 and2015 by use of linear regression model in the Excel functions. In theselection of this technique, I have weighed various factors thatcould have an impact on the variety or the historical trend of thegame attendance. The forecasting technique applied has a highaccuracy level, and this is why I have considered using it. The mainpurpose of this forecasting is to present an overview of the expectedrevenue from the football game attendance. I have preferred the useof quantitative model since this approach mainly concerns solely withthe available data and ignores the fickleness of the participants andconcentrate on the underlying data to predict the future trend.

Question2

Thefollowing are the expected revenues for the year 2014 and 2015 (seethe workings in the excel spreadsheet attached)

 Year Game Total attendance Price Revenue 1 2 3 4 5 2014 48,453 51,571 46,983 35,583 49,148 231,739 20 \$4,634,779 2015 51,496 53,237 48,019 37,708 51,878 242,338 21 \$5,089,094

Fromthe workings, the expected revenue is \$4,634,779. This amount isarrived at by multiplying the expected attendance of each game by theticket price.

Questionthree

School’soptions

Salesforecasting refers to the prediction of the number or set of numbersthat corresponds to a future occurrence. It is an important tool ofmanagement as it helps in decision making especially when building upproduction budgets. Sales forecasting helps the managers in coming upwith close estimations of the expected demand. It is, therefore,important to ensure a high level of accuracy when predicting thefuture sales level. As forecast horizon shortens, the forecastaccuracy increases. Since the case of the firm discussed hereembraces monthly forecasting, we also expect that the accuracy isrelatively high.

Casestudy 2

Question1

Thetrend

Thetrend has shown that the revenue decreases from January to Septemberand then starts increasing over the year (see the graph). Thisimplies that the sales of the Glass Slipper is seasonal, and it ishigh at the beginning and the end of each year. The regressionanalysis has shown that the revenue is at the lowest point during themonth of September after that it starts rising gradually.

Questiontwo

Thetrend line

Thetrend developed for the year 2014 through regression analysis is moresimilar to that of question one above. The trend line has a negativeslope just like that of the previous analysis. However, the slope ofthis line is constantly sloping downward because the forecastinganalysis used, in this case, is a linear regression.

Question3

Multiplicativemodel

Thisis an estimation of the future trend of revenue by taking intoaccount the four components of a time series (Douglass, William &ampWathen, 2011). These components include the trend, the cyclicalvariation the seasonal variation and the irregular variation.

SecularTrend T- this is a long-term direction of a time series. It shows thegeneral movement of the activities of the firm by clearly indicatingthe down swings and the upswings.

Cyclicvariation C – this is a rise or fall in time series for one year.Normal operations of any business are faced with recession,depression and after that recovery.

Seasonalvariation – this shows the pattern of change in time series withina year. In this case, the firm has a pattern that is repeating itselfeach year.

Irregularvariation – this represents the unpredictable fluctuations in theexpected trend.

Toobtain the forecasted values for the year 2014, we can usemultiplicative model. This is done by multiplying the four componentsof the time series that is

Y= T × C × S × I

Seethe table below

 Period Monthly Revenue (\$1000s) month 2011 2012 2013 Centered Moving Average Ratio to CMA seasonal index 2014 Sales Deseasonalized 1 January 438 444 450 2 February 420 425 438 3 March 414 423 434 441 0.984871 0.984871407 434 4 April 318 331 338 403 0.838017 0.838016529 338 5 May 306 318 331 368 0.900272 0.900271985 331 6 June 240 245 254 308 0.825569 0.825568797 254 7 July 240 255 264 283 0.932862 0.932862191 264 8 August 216 223 231 250 0.925234 0.925233645 231 9 September 198 210 224 240 0.934631 0.934631433 224 10 October 225 233 243 233 1.044413 1.044412607 243 11 November 270 278 289 12 December 315 322 335

Theresulting slope regression analysis is quite different from the oneobtained with multiplicative model. This is because this model tendsto more accurate by taking into account any contributing factor thatcould affect the future revenue.

References

DouglassA., William G. &amp Wathen S. (2011). StatisticalTechniques in Business and Economics fifteenth edition.California: McGraw Hill International.

HeizerJ. and Render B. (2014). OperationManagement 11thedition.Upper Saddle River Pearson.