Assignment 1 [100 marks]

1. Agri-Chem Corporation would like to forecast monthly sales of one of its products.
Sales for the past 12 months are as follows:

Month Sales

Jan 522
Feb 576
Mar 511
Apr 539
May 547
Jun 505
Jul 544
Aug 509
Sep 563
Oct 551
Nov 538
Dec 560
(a) Graph the sales for this product over time. [2 marks]
(b) Compute the forecasts that would have been produced by [4 marks]
(i) a cumulative average and
(ii) a simple moving average with N = 5
(c) Compute the mean absolute deviation and mean squared error for each model
during the last six months. [2 marks]
(d) For the better of the two models, compute a forecast for the next month (January).
[2 marks]

2. Quaker Brand Foods uses oats in some of its cereal products. The price of oats is
volatile, so Quaker would like to forecast the average weekly price. The average
prices per bushel for the past eight weeks are as follows:

Week Average price

/Bushel ($)

1 1.16
2 1.21
3 1.22
4 1.25
5 1.23
6 1.19
7 1.20
8 1.17
 (a) Using the weighted moving average with N = 3and weights of 3/6, 2/6, and 1/6,
compute the forecasts that would have occurred during the past 5 weeks.
[4 marks]
(b) Compute the forecasts that would have occurred using a simple exponential
smoothening model with α = 0.30 and an initial forecast for 1 week of $1.18.
[2 marks]
(c) Compute and compare the mean absolute deviation and mean absolute
percentage error for each model during weeks 5-8. [2 marks]
(d) For the better of the two models, compute a forecast for week 9. [2 marks]

3. The manager of a hotel is considering expanding his hotel. Below are the number
of nights the hotel was at least 95% booked during each of the last seven years.

Year Nights
Booked

1 16
2 21
3 24
4 28
5 32
6 34
7 39

(a) Compute the least squares regression equation that expresses the number of
nights that are 95% booked each year as a linear function of time. [4]
(b) Compute the forecasting errors that would have resulted from the model. [4]
(c) Compute the forecasts for years 8 and 9 using this model. [2]

4. Hans Gumph, the operations vice president for Dynamo Machine Works, would
like to forecast future quarterly demand for drill presses. The number of drill
presses sold on a quarterly basis during the past three years is as follows:

Presses Sold
Year Qt 1 Qt 2 Qt 3 Qt 4

1 120 150 190 180

2 220 240 300 270
3 330 340 410 370

Hans believes there may be some seasonality in the underlying process.

 (a) Construct a linear trend model with multiplicative seasonality for Hans
[3 marks]
(b) Compute the forecasts, errors, mean absolute deviation, and mean squared
error for the model [4 marks]
(c) From these results, would you conclude that seasonality exists? [3 marks]

5. American Electric Company believes that the amount of electricity usage in its
service area during the summer is related to the average daily temperature in the
region (defined as the average of the daily high temperature and daily low
temperature). The following table gives the average daily temperature for 10 days
and the amount of electricity used in the region that day.
a) Construct a linear causal model that expresses electricity usage in a day as
a function of the average temperature that day. [2 marks]
b) Suppose the forecasted high and low temperatures for the next two days
are 88℉ and 70℉ for day 1 and 90℉ and 72℉ for day 2. Forecast the
expected electricity usage each day. [4 marks]
c) Is there a potential problem with using the temperature forecasts in this
model? How should it be corrected? [4 marks]

𝑿𝒊 𝒀𝒊
Day Average Usage
Temperature (000 kwh)
1 81 65
2 84 69
3 85 71
4 78 62
5 75 59
6 76 62
7 81 67
8 80 66
9 85 72
10 83 68

6. The monthly demand for units manufactures by the Acme Rocket Company has
been as follows:

Month Units Month Units

May 100 September 105

June 80 October 110
July 110 November 125
August 115 December 120

a) Use the exponential smoothing method to forecast the number of units for
June to January. The initial forecast for May was 105 units; 𝛂 = 2[4 marks]
 b) Calculate the absolute percentage error for each month from June through
December and the MAD and MAPE of forecast errors of the end of
December. [4 marks]
c) Calculate the tracking signal as of the end of December. What can you say
about the performance of your forecasting method? [2 marks]

7. The demand for Krispee Crunchies, a favorite breakfast cereal of people born in
the 1940s, is experiencing a decline. The company wants to monitor demand for
this product closely as it nears the end of its life cycle. The trend-adjusted
exponential smoothing method is used with 𝛂 = 0.1 and 𝛃 =0.2. At the end of
December, the January estimate for the average number of cases sold per month,
𝑨𝒕 , was 900,000 and the trend, 𝑻𝒕 , was -50,000 per month. The following table
shows the actual sales history for January, February, and March. Generate
forecasts for February, March, and April. [10 marks]

Month Sales

January 890,000
February 800,000
March 825,000

8) The Northville Post Office experiences a seasonal pattern of daily mail volume every
week. The following data for two representative weeks are expressed in thousands of
pieces of mail:
Day Week 1 Week 2

Sunday 5 8
Monday 20 15
Tuesday 30 32
Wednesday 35 30
Thursday 49 45
Friday 70 70
Saturday 15 10

Total 224 210

a) Calculate a seasonal factor for each day of the week. [5 marks]

b) If the postmaster estimates that there will be 230,000 pieces of mail to sort next
week, forecast the volume for each day of the week. [5 marks]

9) A specific forecasting model was used to forecast demand for a product. The forecasts
and the corresponding demand that subsequently occurred are shown as follows. Use the
MAD, tracking signal technique, and MAPE to evaluate the accuracy of the forecasting
model. [10 marks]
Actual Forecast

October 700 660

November 760 840
December 780 750
January 790 835
February 850 910
March 950 890

10) Sunrise Banking Company markets doughnuts through a chain of food stores. It has
been experiencing overproduction and underproduction because of forecasting errors.
The following data are its demand in dozens of doughnuts for the past four weeks.
Doughnuts are made for the following day; for example, Sunday’s doughnut production
is for Monday’s sales, Monday’s doughnut production is for Tuesday’s sales, and so forth.
The bakery is close Saturday, so Friday’s production must satisfy demand for both
Saturday and Sunday. [10 marks]

4 Weeks Ago 3 Weeks Ago 2 Weeks Ago Last week

Monday 2,200 2,400 2,300 2,400

Tuesday 2,000 2,100 2,200 2,200
Wednesday 2,300 2,400 2,300 2,500
Thursday 1,800 1,900 1,800 2,000
Friday 1,900 1,800 2,100 2,000
Saturday (closed on Saturday)
Sunday 2,800 2,700 3,000 2,900

Make a forecast for this week based on the following:

a) Daily, using a simple four-week moving average. [3 marks]
b) Daily, using a weighted moving average with weights of 0.40, 0.30, 0.20, and 0.10
(most recent to oldest week). [3 marks]
c) Sunrise is also planning its purchases of ingredients for bread production. If bread
demand had been forecast for last week at 22,000 loaves and only 21,000 loaves
were actually demanded, what would Sunrise’s forecast be for this week using
exponential smoothing with 𝜶 = 0.10? [2 marks]
d) Suppose with the forecast made in c, this week’s demand actually turns out to
22,500. What would the new forecast be for the next week? [2 marks]