Unit 7: Demand Management and Forecasting

Question 1

What is the difference between dependent and independent demand?

Answer 1

x

Question 2

What is the purpose of demand management?

Answer 2

Demand management is used to control inventory or raw materials and finished goods to maximize profit and ensure that adequate supply is available within reasonable time frames

Question 3

What is time series analysis?

Answer 3

A forecast in which past demand data is used to predict future demand.

Question 4

What are the components of demand? What are trend, seasonal, randomness, and cyclical factors? What is a trend line?

Answer 4

Average demand, trend, seasonal element, cyclical elements, random variation and autocorrelation0

Question 5

What are four of the most common trends? Refer to Exhibit 18.2.

Answer 5

• S curve
• Asymptotic
• Exponential
• Linear

Question 6

What is time series forecasting?

Answer 6

Tries to predict the future based on past data

Question 7

How should a firm decide as to which forecasting model to choose? Review Exhibit 18.3.

Answer 7

1. Time horizon to forecast
2. Data availability
3. Accuracy required
4. Size of forecasting budget
5. Availability of qualified personnel

Question 8

What is simple moving average forecasting? Review Formula 18.1. Review Exhibit 18.4 which shows an example of simple moving average forecasting using a three- and a nine-week period. Note Exhibit 18.4 also plots actual demand against the moving average forecast.

Answer 8

The idea here is to simply
calculate the average demand over the most recent periods. Each time a new forecast is
made, the oldest period is discarded in the average and the newest period included.

Question 9

How does a simple moving average forecast differ from a weighted moving average forecast? Review Formula 18.2 and the discussion about it. How should weights for the calculation be chosen?

Answer 9

A weighted average forecast places different gain factors on certain items or time periods in the the forecast. A simple moving average has the same weight for each

Question 10

How does exponential smoothing differ from the weighted and simple moving average forecast? What are the six major reasons for the acceptance of exponential smoothing techniques? How is exponential smoothing accomplished? Why are exponential smoothing models accurate?

Answer 10

A time series forecasting 
technique using 
weights that decrease 
exponentially (1 – α) for 
each past period. This allows the oldest observation to be dropped in each iteration which keeps a consistent amount of historical data instead of accumulating it.

Question 11

What are the three pieces of data required to forecast the future with exponential smoothing? Review Formula 18.3. Review Exhibit 18.5. What is the smoothing constant ()? (Note: You will not be required to develop a forecast using exponential smoothing, but you must know how it differs from weighted moving average forecasting and its advantages over the other methods of forecasting.)

Answer 11

The most recent forecast, the actual demand that occurred for that forecast period, and
a smoothing constant alpha (α)

Ft = Ft−1 + α(At−1 − Ft−1 )
where
Ft = The exponentially smoothed forecast for period t
Ft−1 = The exponentially smoothed forecast made for the prior period At−1 = The actual demand in the prior period
α = The desired response rate, or smoothing constant

Question 12

Why is a trend adjustment necessary in exponential forecasting? What does the smoothing constant delta () accomplish?

Answer 12

Exponential smoothing lags changes in demand: during an increase or decrease it lags, but overshoots when a change in direction occurs. The higher the value of alpha the closer the forecast follows the actual.

Alpha gives the desired response rate, because it is a factor applied to the error in guessing the previous forecast vs the actual outcome.

Question 13

Work through the solution to Example 18.1. How can you get a trend formula going to make the initial forecast?

Answer 13

x

Question 14

How is the appropriate value for alpha chosen?

Answer 14

Exponential smoothing requires that the smoothing constants be given a value between 0
and 1. Typically, fairly small values are used for alpha and delta in the range of .1 to .3. The
values depend on how much random variation there is in demand and how steady the trend
factor is.

Question 15

Review the sections on forecast errors, their sources, and how to measure them

Answer 15

x

Question 16

What is the mean absolute deviation (MAD) and how is it used in forecasting? (Note: You must have a cursory understanding of MAD but you will not be required to use it in forecasting problems.)

Answer 16

x

Question 17

What is a tracking signal?

Answer 17

x

Question 18

What is regression analysis? What is the major restriction in using linear regression forecasting? Under what conditions is it useful to use linear regression?

Answer 18

-  Linear regression refers to 
the special class of regression where the relationship between variables forms a straight line.
The linear regression line is of the form Y = a + bt, where Y is the value of the dependent variable that we are solving for, a is the Y intercept, b is the slope, and t is an index for the time period.

• The major restriction in using linear regression forecasting is, as the name implies, that past
  data and future projections are assumed to fall in about a straight line
• linear regression is useful for long-term forecasting of major occurrences and aggregate
  planning.

Question 19

Work through the solution to Example 18.2. Review Exhibits 18.6 to 18.8 and notice how Excel is used to provide rapid solutions. As the textbook mentions, Microsoft Excel has a powerful regression routine to perform these calculations (see Exhibit 18.8).
Read the section at the bottom of page 458 of your textbook which discusses the Excel spreadsheet.

Answer 19

ok

Question 20

What is meant by decomposition of a time series? What is meant by the two types of seasonal variation, multiplicative and additive? What is a seasonal factor? See Exhibit 18.9 and note the effect of using the additive versus the multiplicative method of integrating seasonal variation data.

Answer 20

Decomposition of a time series identifies and separates the time series data into components.

Additive adds the trend to the seasonal value, whereas multiplicative multiplies it.

The seasonal factor is the amount of correction needed in a time series to adjust for the season of the year.

Question 21

How are seasonal indexes determined? Work through the solution to Example 18.3.

Answer 21

Seasonal factor = past sales (for that season) / (Average sales for each season)

Question 22

How are trend and seasonal factors from a hand-fit straight line computed? Work through Example 18.4.

Answer 22

• Find the forecast including trend equation
• Take the ratio: (actual / trend) for each quarter
• Take the average of the same quarter’s ratios

Question 23

Exhibit 18.10 shows the points plotted in a graph. The trend line is calculated by measuring the slope of the line. Once you have the trend line, you can calculate the figures on the trend line as shown in Exhibit 18.10. Next, calculate the seasonal factors. With the seasonal factors you can then develop the forecast for the four quarters in 2013 as shown in Exhibit 18.10.

Answer 23

y

Question 24

What are the steps used in the decomposition of a time series using the least squares regression method? Follow the five steps outlined on pages 461 to 463 to create the final forecast, noting how the seasonal factor is determined under Step 1. Review Exhibit 18.11, which shows the results of the five steps in table format. The same data used in the previous example is shown. Finally, look at how the trend line formula (Y = a + bx) is developed at the bottom of Exhibit 18.11.

Answer 24

1) Determine the seasonal factor or index ( develop an average for the same quarters in the three-year period. Derive the seasonal factor by dividing that average by the general average for all 12 quarters
2) Deseasonalize the data. Divide the original date by the seasonal factor.
3) Develop a least squares regression for the deseasonalized data.
Y = a + bt

b = ∑(t y − n¯t· y¯)/∑(t^2 − n¯t^2)

a = y¯ − b¯

4) Project the regression line through the period to be forecast
5) Adjust the regression line by the seasonal factor

Question 25

What might a graph of the deseasonalized question look like? Review Exhibit 18.12, which shows one.

Answer 25

y

Question 26

How do sources of error develop? Review Exhibit 18.13. Note the discussion of “error range” on page 46

Answer 26

• Lack of historical data/ past trends
  Bias errors occur when a consistent mistake is made.
  Sources of bias include the failure to include the right variables; the use of the wrong relationships among variables; employing the wrong trend line; a mistaken shift in the seasonal demand from where it normally occurs; and the existence of some undetected secular
  trend.

Random errors can be defined as those that cannot be explained by the forecast model being used.

Question 27

What is meant by causal relationship forecasting? Work through the solution to Example 18.5. Note how the data is plotted in Exhibit 18.16.

Answer 27

Forecasting using
independent variables
other than time to predict
future demand.

Question 28

What is multiple regression analysis?

Answer 28

multiple regression analysis, in which a number of variables are considered, together with the effects
of each on the item of interest.

Question 29

What are the four qualitative techniques in forecasting?

Answer 29

Market research, panel consensus, historical analogy, delphi method

Question 30

How is CPFR used and what are its objectives? What are the five steps of CPFR?

Answer 30

Collaborative planning, forecasting, and replenishment (CPFR) An Internet tool to coordinate forecasting, production, and purchasing in a firm’s supply chain.

Step 1. Creation of a front-end partnership agreement
Step 2. Joint business planning.
Step 3. Development of demand forecasts.
Step 4. Sharing forecasts
Step 5. Inventory replenishment.

Question 31

Work through Solved Problems 1 and 2 on pages 473–475 in the textbook.

Work through Objective Questions 14, 15, and 24 at the end of Chapter 18 (pages 505–506). When you get to Objective Question 24, first review the solution provided below, then enter the data into the Excel spreadsheet that you opened earlier in the chapter. See that you get the same solution.

Answer 31

x