CHAPTER 4 FORECASTING DEMAND 177 Problems Note: (xe means the problem may be solved with POM for Windows and/or Excel OM. =+ 4.1 The Carbondale Hospital is considering the purchase ‘of « new ambulance. The decision will rest partly on the antici- ‘pated mileage to be driven next year. The miles driven during the past 5 years are as follows Cs 3,000 a0 3,400 3,800 3,700 =) Forecast the mileage for next year (6th year) usiggg a 2-year ‘moving average. >) Find the MAD based on the 2-year moving average. (Hint ‘You will have only 3 years of matched data.) © Use a weighted 2-year moving average with weights of 4 20d 6 to forecast next year’s mileage. (The weight of .6 is for the most recent year.) What MAD results from using this ‘pproach to forecasting? (Hint: You will have only 3 years of matched data.) © Compute the forecast for year 6 using exponential smoothing, ‘== initial forecast for year 1 of 3,000 miles, and a = 5. PAC ies, Inc., were as January february a Mach 5 Apa 4 May a ne 16 ay 7 Ags ie September 2 October 2 November a December 2 ‘@) Plot the monthly sales data, ‘> Forecast January sales using each of the following: @ Naive method. ® ASmonth moving average. &) A &month weighted average using .1, .1, -1, 2,2. and 3, with the heaviest weights applied to the most recent months. =) Exponential smoothing using an a = .3 and a September forecast of 18, =) A trend projection. © Wee the data given, which method would allow you to fore- es next March’s sales? PX 4) Plot the data on a graph, Do you observe any trend, eycles, or random variations? b) Starting in year 4 and going to year 12, forecast demand using ‘a 3-year moving average. Plot your forecast on the same graph as the original data. ©) Starting in year 4 and going (o year 12, forecast demand using ‘a 3-year moving average with weights of 1, 3, and .6, using .6 for the most recent year. Plot this forecast on the same graph. 4) As you compare forecasts with the original data, which seems to give the better results? P< ++ 44 The actual demand for the patients at Omaha Emer- ‘gency Medical Clinic for the first 6 weeks of this year follows: weex 1 2 Gy 3 70 4 48 5 8 6 32 Clinic administrator Mare Schniederjans wants you to forecast patient demand at the clinic for week 7 by using this data. You decide to use a weighted moving average method to find this fore- cast. Your method uses four actual demand levels, with weights of 0.333 on the present period, 0.25 one period ago, 0.25 two peri- ‘ods ago, and 0.167 three periods ago. a) What is the value of your forecast? PX bb) Ifinstead the weights were 20, 15, 15, and 10, respectively, how ‘would the forecast change? Explain why. c) What if the weights were 0.40. 0.30, 0.20, and 0.10, respec- tively? Now what is the forecast for week 7? + 48 The following gives the number of pints of type B blood used at Woodlawn Hospital in the past 6 weeks: Ca ‘August 31 360 Septembec 7 380 September 14 410 September 21 381 September 28 368 october 5 374 a) Forecast the demand for the week of October 12 using a 3aweek moving average. b) Usea 3-week weighted moving average, with weights of 1,3. ‘and .6, using .6 for the most recent week. Forecast demand for the week of October 12. ©) Compute the Forecast for the week of October 12 using exponenti smoothing with a forecast for August 31 of 360 and a = .2. Pe © 46 — Refer to Problem 4.3. Develop a forecast for years 2 through 12 using exponential smoothing with a = .4 and a fore- cast for year | of 6, Plot your new forecast on a graph with the actual data and the naive forecast, Based on a visual inspection, which forecast is better? PAC178 PARTI + 47 A check-processing cemter uses exponential smooth- ing to forecast the number of incoming checks each month. The ‘number of checks received in June was 40 million, while the fore. cast was 42 million, A smoothing constant of 2 is used. a) What is the forecast for July? b) AP the center received 45 million checks in July, what would be the forecast for August? ©) Why might this be an inappropriate forecasting method for this situation? PX + 48 Daily high temperatures in St. Louis for the last week were as follows: 93, 94, 93, 95, 96, 88, 90 (yesterday). a) Forecast the high temperature today, using a 3-day moving 'b) Forecast the high temperature today, using a 2-day moving average. ©) Calculate the mean absolute deviation based on @ ing average. ) Compute the mean squared error for the 2-day moving average, ©) Calculate the mean absolute percent error for the 2-day mov ing average. day mov- ++ 4.9 Data collected on the yearly registrations for a Six Sigma seminar at the Quality College are shown in the following table 89 wn 9 24 ) Develop a 3-year moving average to forecast registrations from year 4 10 yeur 12. b) Estimate demand again for years 4to 12 with a 3-year weighted ‘moving average in Which registrations in the most recent year lt of 2, and registrations in the other 2 years are each given a weight of I ©) Graph the original data and the two foreca two forecasting methods seems better? PX 's. Which of the + 4.40 Use exponential smoothing with a smoothing con. stant of 0.3 to forecast the registrations at the seminar given in Problem 4.9, To begin the procedure, assume that the forecast for year 1 was 5.000 people signing up. a) What is the MAD? PC ) What is the MSE? ++4.44 Consider the following actual and forecast demand levels for Big Mac hamburgers at a local McDonald’ restaurant o cr Monday 88 a8 Tuesday n 88 Weenestay a 4 Thursday 4% 20 Fray 1 Monday's demand level and setting Monday's forecast level equal to this demand level. Subsequent forecasts were derived by using expo- nential smoothing with a smoothing, constant of 0.25. Using this exponential smoothing method, what is the forecast for Big Mac demand for Friday? Poe ++4,12 Lenovo uses the ZX-81 chip in some of its laptop computers. The prices for the chip during the past 12 months: were as follows: INTRODUCTION TO OPERATIONS MANAGEMENT ers PRICE PER oe Janay $1.80 [duly 1.80 Februay 187 | August 1.83 Ma 170 | September 1.70 a 195 | occber 1.65 Ma 190 | November 1.70 dune jonth moving average on all the data and plot the sand the prices. nonth moving average and add the 3-month plot fo ne graph ereated in part (a), ©) Which is better (using the mean absolute deviation): the 2month average or the 3-month average? Compute the forecasts for each month using exponentia! smoothing, with an initial forecast for January of $1.80, Use = 1, then « = .3, and finally a = .5, Using MAD, which isthe best? PO + 4.43 As you can see in the following table, demand fe heart transplant surgery at Washington General Hospital bs increased steadily in the past few years ‘The director of medical services predicted 6 years ago th demand in year | would be 41 surgeries. E & 3 4) Use exponential smoothing, first with a smoothing constant of .6 and then with one of 9, to develop forecasts for years hrough 6, b) Use a 3-year moving average to forecast demand in years 4 S and 6. ©) Use the trend-projection method to Forecast demand in years through 6. ) With MAD as the criterion, which of the four forecasting methods is best? Poe ++ 4.14 Following are two weekly forecasts made by two dif ferent methods for the number of gallons of gasoline, in thow- sands, demanded at a local gasoline station. Also shown are actual demand levels, in thousands of gallons.FORECASTS ood fom) 1 0.90 0.80 0. 2 1.05 120 1.00 3 035 090 1.00 4 120 1a 1.00 What are the MAD and MSE for each method? 4.45 Refer to Solved Problem 4.1 on page 174 2) Use a 3-year moving average to forecast the sales of ‘Volkswagen Beetles in Nevada through year 6. 5) What is the MAD? P< =) What isthe MSE? 4.46 — Refer to Solved Problem 4.1 2) Using the trend projection (regression) method, develop a fore- cast for the sales of Volkswagen Beetles in Nevada through year 6 5) What is the MAD? Pac 2) What is the MSE? +447 Sales of quilt covers at Bud Banis’s department store in Carbondale over the past year are shown below. Management prepared a forecast using a combination of exponential smooth- ing and its collective judgment for the 4 months (March, April, May, and June): COMET Cen wy 100 August 3 September 96 October 110 Noverber 124 December 119 Janvary 92 February 3 March 101 120 orl 96 114 May 20 110 une 108 108 2) Compute MAD and MAPE for management's technique b) Do managements results outperform (ie., have smaller MAD and MAPE than) a naive forecast? =) Which forecast do you recommend, based on lower forecast error? * 4.48 _ Refer to Solved Problem 4.1. Using smoothing con- stants of 6 and .9, develop forecasts for the sales of VW Beetles. What effect did the smoothing constant have on the forecast? Use MAD to determine which of the three smoothing constants (3, 6, or 9) gives the most accurate forecast. PC Consider the following actual (4,) and forecast (F,) demand levels for a commercial multiline telephone at Office Max: CHAPTER 4 FORECASTING DEMAND 179 The first forecast, F;, was derived by observing 4, and setting F, equal to 4,. Subsequent forecast averages were derived by expo- nential smoothing. Using the exponential smoothing method, find the forecast for time period 5. (Hint: You need to first find the smoothing constant, a.) 4.20 Income at the architectural fitm Spraggins and Yunes for the period February to July was as follows: To CL (nema | 700 eas | eas (ir | 11a] 728 Use trend-adjusted exponential smoothing to forecast the firm’s August income. Assume that the initial forecast average for February is $65,000 and the initial trend adjustment is 0. The smoothing constants selected are « = .1 and B = .2. PC ss+4.21 Resolve Problem 4.20 with a = .1 and B = 8. Using MSE, determine which smoothing constants provide a better forecast, Pac + 4.22 Refer to the trend-adjusted exponential smoothing illustration in Example 7 on pages 153-155. Using « = .2 and B = 4, we forecast sales for 9 months, showing the detailed caleu- lations for months 2 and 3, In Solved Problem 4.2, we continued the process for month 4. In this problem, show your caleulations for months Sand 6 for Fp Ty and FIT, PX + 4.23 The number of internal disk drives (in millions) made ata plant in Taiwan during the past 5 years follows: co co 1 140 2 160 3 190 4 200 5 210 ) Forecast the number of disk drives to be made next year, using linear reatession b) Compute the mean squared error (MSE) when using linear regression «) Compute the mean absolute percent error (MAPE). PAC + 4.24 Refer to Problem 422. Complete the trend-adjusted éexponential-smoothing forecast computations for periods 7, 8, and 9. Confirm that yout numbers for F, 7, and FIT, match those in Table 4.1 (p. 154). Pa £4.28 Mark Gershon, owner of a musical instrument ise tributorship, thinks that demand for guitars may be related to the number of television appearances by the popular group Maroon 5 during the previous month. Mark has collected the data shown in the following table: Sn a] soa uae iano | 7 [cea 2? 1 2 2 50 a 56 4 4 46 50 5 a) Graph these data to see whether a linear equation might describe the relationship between the group's television shows and guitar sales, ») Use the least-squares regression method to derive a forecasting equation,180 PART? ©) What is your estimate for guitar sale if Maroon 5 performed ‘on TV nine times last month? 4) What are the correlation coefficient (r) and the coefficient of determination (for this model, and what do they mean? P2¢ + 4.26 The following gives the number of accidents that cceurred on Florida State Highway 101 during the past 4 months: cn Pe January 20 February 40 Mach 6 pr 0 Forecast the number of accidents that will oceur in May, using least-squares regression to derive a trend equation ++ 4.27 George Kyparisis owns @ company that manufactures sailboats. Actual demand for George’ sailboats during each of the past four seasons was as follows YEAR Winter 1400. 1,200 1000900 sping 1500 1400 1,600 1,500 Summer 1,000. 2,100 2000 1,900, “rll 600 | 750-650 500 George has forecasted that annual demand for his sailboats in year 5 will equal 5,600 sailboats. Based on this data and the ‘multiplicative seasonal model, what will the demand level be for ‘George's sailboats in the spring of year 5? 4,28 Attendance at Orlando’s newest Disneylike attrac- tion, Lego World, has been as follows: Cr ot OO a ec ee ‘Wires Year 1 73 Summer Year? na Spring Year 1 ros | all Year 52 SummerYear! 168 | intr Yoor 3 9 FallYear 74 | Spring Year 3 16 winter Yoat 2 65 | Summer Year) 205 Spring Year 2 rallYeor3 98 Compute seasonal indices using all of the data, Pc + 4.29 North Dakota Electic Company estimates its demand trendline (in milions oF kilowatt hours) tbe D=71+0439 where Q refers to the sequential quarter number and @ = | for winter of Year I. In addition, the multiplicative seasonal factors are as follows: Witer 8 ping ul summer 14 fal 7 Forecast eneray use for the four quarters of year 25, beginni swith winter. INTRODUCTION TO OPERATIONS MANAGEMENT + 490 In the past, Poter Kelle’s tire dealership in Baton Rouge sold an average of 1,000 radials each year. In the past 2 years, 200 and 250, respectively, were sold in fll, 350 and 300 in ‘winter, 150 and 165 in spring, and 300 and 285 in summer. With = ‘major expansion planned, Kelle projects sles nent year to increase to 1,200 radials. What wil be the demand during each season? + 4.31 Lori Cook has developed the following forecast model: p=. +43 where demand for Kool Air conditioners and the outside temperature °F) PC 4) Forecast demand for the Kool Air when the temperature is 10°F 'b) What is demand when the temperature is 80°F? ©) What is demand when the temperature is 90°F? PoC ++4.32 Calé Michigan’s manager, Gary Stark, suspects that demand for mocha latte coffees depends on the price beins charged. Based on historical observations, Gary has gathered the following data, which show the numbers of these coffees sold over six different price values a ner $270 780 $3.50 5310 $2.00 80 420 250 83.10 20 $8.05 480 Using these data, how many mocha tatte coffees would be fore casi {0 be sold according to simple linear regression if the price per cup were $2,80? PC + 4.33 The following data relate the sales figures of the bar in Mark Kaltenbach’s small bed-and-breakfast inn in Portand, fo the number of guests registered that week: 1 16 $330) 2 2 20 3 18 30 4 14 300 a) Meform a tinear regression that relates bar sales to guests (not to time), >) Ifthe forecast is for 20 guests next week, whut are the sales expected to be? Poe + 4.34 The number of auto accidents in Athens, Ohio, is related tothe regional numberof registered automobiles in thou sands (X),aleoholie beverage sales in $10,000s (X,), and rainfall in inches (14). Furthermore, the regression formula has been cal culated as Ysat bX + this + Xs where Y= number of automobile accidents a=15 eas b= 45 by, =25