lecture 9

Question 1

components of demand

Answer 1

Average, trend, seasonal element, cycles, random variation, autocorrelation

Question 2

Time series analysis (choose depending on)

Answer 2

time horizon

data availability

Qualified personnel

Accuracy required

Budget

other…

Question 3

Simple moving average (quantitative forecast models)

Answer 3

Decisoins: Period (week, months), period length (n)

Formula =

Ft = At-1 + At-2 + At-3 + … + At-n

If asked for three week moving average it means just take the latest scores

Question 4

Weighted moving average
(quantitative forecast models)

Answer 4

Decisions: period (week, months), period length (n), weights

Formula =

Ft = w1At-1 + w2At-2 + … + wnAt-n

Example 2

Using the customer- arrival data from example 2, let
W1 = 0.50, W2 = 0.30, and W3 = 0.20. Use the weighted moving average method to
forecast arrivals for month 5.

Question 5

Exponential smoothing
(quantitative forecast models)

Answer 5

Decisions: period (week, months), smoothing constant alpha, starting values

Formula =

Ft = Ft-1 + alpha(At-1 - Ft-1)

E.g.

Suppose that in month 4 the forecast was for 783 arrivals. Use exponential smoothing with alpha = 0.2 to compute the forecast in month 5

Question 6

Exponential smoothing with Trend:
(quantitative forecast models)

Answer 6

Decisions: period (week, months), smoothing constant alpha and omega, starting values

Formula =

Ft = FITt-1 + alpha(At-1 - FITt-1)

Tt = Tt-1 + omega(Ft - FITt-1)

FITt = Ft + Tt

Question 7

Linear regression analysis
(quantitative forecast models)

Answer 7

Predict one variable given the otehr: demand vs time (time series) deamand vs price (causal relationship)

relationship forms a straight line Yt = a + bt

Useful: long term, aggregate planning

E.g. use excel to calculate the linear regression equation

Estimate the sales for a price of 3.00$ per dinner

Question 8

Qualitative forecast models

Delphi method

Answer 8

Choose the experts to participate: there should be a variety of knowledgeable people in different areas

Through a questionnaire or email, obtain forecasts (and any premises or qualifications for the forecasts) from all participants

Summarize the results and redistribute them to the participants along with appropriate new questions

Summarize agian, refining forecasts and conditions, and again develop new questions

Repeat step 4 i fnecessary. Distribute the final results to all participants