1. Demand Management and FORECASTING
Operations Management
Dr. Ron Lembke

2. Demand Management
Coordinate sources of demand for supply chain to run efficiently, deliver on time
Independent Demand
Things demanded by end users
Dependent Demand
Demand known, once demand for end items is known

3. Affecting Demand Increasing demand Changing Timing of demand
Marketing campaigns
Sales force efforts, cut prices
Changing Timing of demand
Incentives for earlier or later delivery
At capacity, don’t actively pursue more

4. Predicting the Future We know the forecast will be wrong.
Try to make the best forecast we can,
Given the time we want to invest
Given the available data
The “Rules” of Forecasting:
The forecast will always be wrong
The farther out you are, the worse your forecast is likely to be.
Aggregate forecasts are more likely to accurate than individual item ones

5. Time Horizons
Different decisions require projections about different time periods:
Short-range: who works when, what to make each day (weeks to months)
Medium-range: when to hire, lay off (months to years)
Long-range: where to build plants, enter new markets, products (years to decades)

6. Forecast Impact
Finance & Accounting: budget planning Human Resources: hiring, training, laying off employees Capacity: not enough, customers go away angry, too much, costs are too high Supply-Chain Management: bringing in new vendors takes time, and rushing it can lead to quality problems later

7. Qualitative Methods Sales force composite / Grass Roots
Market Research / Consumer market surveys & interviews
Jury of Executive Opinion / Panel Consensus
Delphi Method
Historical Analogy - DVDs like VCRs
Naïve approach

8. Quantitative Methods
Time Series Methods 0. All-Time Average 1. Simple Moving Average 2. Weighted Moving Average 3. Exponential Smoothing 4. Exponential smoothing with trend 5. Linear regression Causal Methods Linear Regression

9. Time Series Forecasting
Assume patterns in data will continue, including:
Trend (T)
Seasonality (S)
Cycles (C)
Random
Variations

10. All-Time Average
To forecast next period, take the average of all previous periods Advantages: Simple to use Disadvantages: Ends up with a lot of data Gives equal importance to very old data

11. 4/7/2009 2009 Farm Angels: Ty: 1.000, Jacob 0.833, Noah 0.667
(6 at bats)

12. End of 2008 season

13. Moving Average Compute forecast using n most recent periods
Jan Feb Mar Apr May Jun Jul
3 month Moving Avg:
June forecast:
FJun = (AMar + AApr + AMay)/3
If no seasonality, freedom to choose n
If seasonality is N periods, must use N, 2N, 3N etc. number of periods

14. Moving Average Advantages: Disadvantages:
Ignores data that is “too” old
Requires less data than simple average
More responsive than simple average
Disadvantages:
Still lacks behind trend like simple average, (though not as badly)
The larger n is, more smoothing, but the more it will lag
The smaller n is, the more over-reaction

15. Simple and Moving Averages

16. Centered MA CMA smoothes out variability
Plot the average of 5 periods: 2 previous, the current, and the next two
Obviously, this is only in hindsight
FRB Dalls graphs

17. Centered Moving Average
Take average of n periods,
Plot the average in the middle period
Not useful for forecasting
More stable than actuals
If seasonality, n = season length (4wks, 12 mo, etc.)

18. CMA - # Periods to Average
What if data has 12-month cycle?
Ja F M Ap My Jn Jl Au S O N D Ja F M
Avg of Jan-Dec gives average of month 6.5: ( )/12=6.5
Avg of Feb-Jan gives average of month 6.5: ( )/12=7.5
How get a July average? Average of other two averages

19. Stability vs. Responsiveness
Real-time accuracy
Market conditions
Stable
Forecasts being used throughout the company
Long-term decisions based on forecasts
Don’t whipsaw those folks

20. Centered Moving Average
To center even-number of periods
12: take half each of 1 and 13, plus sum of 2-12.
F14 = 0.5 A1 + A2 + A3 + A4 + A5 + A6 + A7 + A8 + A9 + A10 + A11 + A A13
This is exactly the same as what you get by taking the average of the averages from previous slide

21. Old Data
Comparison of simple, moving averages clearly shows that getting rid of old data makes forecast respond to trends faster Moving average still lags the trend, but it suggests to us we give newer data more weight, older data less weight.

22. Weighted Moving Average
FJun = (AMar + AApr + AMay)/3
= (3AMar + 3AApr + 3AMay)/9
Why not consider:
FJun = (2AMar + 3AApr + 4AMay)/9
FJun = 2/9 AMar + 3/9 AApr + 4/9 AMay
Ft = w1At-3 + w2At-2 + w3At-1
Complicated:
Have to decide number of periods, and weights for each
Weights have to add up to 1.0
Most recent probably most relevant, gets most weight
Carry around n periods of data to make new forecast

23. Weighted Moving Average
Wts = 0.5, 0.3, 0.2

24. Setting Parameters Weighted Moving Average Trial and Error
Number of Periods
Individual weights
Trial and Error
Evaluate performance of forecast based on some metric

25. Exponential Smoothing
F10 = F (A9 - F9)
F10 = 0.8 F (A9 - F9)
At-1 Actual demand in period t-1 Ft-1 Forecast for period t-1  Smoothing constant >0, <1 Forecast is old forecast plus a portion of the error of the last forecast. Formulas are equivalent, give same answer

26. Exponential Smoothing
Smoothing Constant between
Easier to compute than moving average
Most widely used forecasting method, because of its easy use
F1 = 1,050,  = 0.05, A1 = 1,000
F2 = F1 + (A1 - F1)
= 1, (1,000 – 1,050)
= 1, (-50) = 1,047.5 units
BTW, we have to make a starting forecast to get started. Often, use actual A1

27. Exponential Smoothing
Alpha = 0.3

28. Exponential Smoothing
Alpha = 0.5

29. Exponential Smoothing
We take:
And substitute in
to get:
and if we continue doing this, we get:
Older demands get exponentially less weight

30. Choosing 
Low : if demand is stable, we don’t want to get thrown into a wild-goose chase, over-reacting to “trends” that are really just short-term variation
High : If demand really is changing rapidly, we want to react as quickly as possible

31. Averaging Methods Simple Average Moving Average
Weighted Moving Average
Exponentially Weighted Moving Average (Exponential Smoothing)
They ALL take an average of the past
With a trend, all do badly
Average must be in-between 30 20 10

32. Trend-Adjusted Ex. Smoothing

33. Trend-Adjusted Ex. Smoothing
Forecast including trend for period 1 is
Suppose actual demand is 115, A1=115

34. Trend-Adjusted Ex. Smoothing
Forecast including trend for period 2 is
Suppose actual demand is 120, A2=120

35. FIT5=F5+T5 F6 A5 F5

36. Selecting  and  You could:
Try an initial value for each parameter.
Try lots of combinations and see what looks best.
But how do we decide “what looks best?”
Let’s measure the amount of forecast error.
Then, try lots of combinations of parameters in a methodical way.
Let  = 0 to 1, increasing by 0.1
For each  value, try  = 0 to 1, increasing by 0.1

37. Evaluating Forecasts
How far off is the forecast? What do we do with this information?
Forecasts
Demands

38. Measuring the Errors Method 1 forecasts are low, high, etc.
Period
A-F
Method 1
Method 2 1
100 10 2
-100 3 4 5 6 7 8 9
RSFE
Method 1 forecasts are low, high, etc.
Method 2 forecasts always too low.
Running Sum of Forecast Errors, RSFE
Sum of all periods
Also known as the Bias

39. Evaluating Forecasts
Mean Absolute Deviation Mean Squared Error Percent Error

40. MAD of examples MAD shows that method 1 is off by a larger amount
Period
|A-F|
Method 1
Method 2 1
100 10 2 3 4 5 6 7 8 9
MAD
MAD shows that method 1 is off by a larger amount
Method 2 was biased
However, overall, Method 2 seems preferable

41. Tracking Signal To monitor, compute tracking signal
If >4 or <-4 something is wrong
Top should sum to 0 over time. If not, forecast is biased.

42. Monitoring Forecast Accuracy
Monitor forecast error each period, to see if it becomes too great 4
Upper Limit
Forecast Error -4
Lower Limit
Forecast Period

43. Updating MAD
Simplified calculation avoids keeping running total of all errors and demands:
Standard Deviation can be estimated from MAD:

44. Techniques for Trend
Determine how demand increases as a function of time
t = periods since beginning of data
b = Slope of the line
a = Value of yt at t = 0

45. Computing Values

46. Linear Regression Four methods Fits a trend and intercept to the data.
Type in formulas for trend, intercept
Tools | Data Analysis | Regression
Graph, and R click on data, add a trendline, and display the equation.
Use intercept(Y,X), slope(Y,X) and RSQ(Y,X) commands
Fits a trend and intercept to the data.
R2 measures the percentage of change in y that can be explained by changes in x.
Gives all data equal weight.
Exp. smoothing with a trend gives more weight to recent, less to old.

47. Causal Forecasting
Linear regression seeks a linear relationship between the input variable and the output quantity.
For example, furniture sales correlates to housing sales
Not easy, multiple sources of error:
Understand and quantify relationship
Someone else has to forecast the x values for you

48. Video sales of Shrek 2?
Shrek did $500m at the box office, and sold almost 50 million DVDs & videos
Shrek2 did $920m at the box office

49. Video sales of Shrek 2? Assume 1-1 ratio:
920/500 = 1.84
1.84 * 50 million = 92 million videos?
Fortunately, not that dumb.
January 3, 2005: 37 million sold!
March analyst call: 40m by end Q1
March SEC filing: 33.7 million sold. Oops.
May 10 Announcement:
In 2nd public Q, missed earnings targets by 25%.
May 9, word started leaking
Stock dropped 16.7%

50. Lessons Learned Flooded market with DVDs Guaranteed Sales 5 years ago
Promised the retailer they would sell them, or else the retailer could return them
Didn’t know how many would come back
5 years ago
Typical movie 30% of sales in first week
Animated movies even lower than that
2004/ % in first week
Shrek 2: 12.1m in first 3 days
American Idol ending, had to vote in first week

51. The Human Element
Colbert says you have more nerve endings in your gut than in your brain
Limited ability to include factors
Can’t include everything
If it feels really wrong to your gut, maybe your gut is right

52. Washoe Gaming Win, 1993-96 What did they mean when they
said it was down
three quarters
in a row?

53. Seasonality Seasonality is regular up or down movements in the data
Can be hourly, daily, weekly, yearly
Naïve method
N1: Assume January sales will be same as December
N2: Assume this Friday’s ticket sales will be same as last

54. Seasonal Factors
Seasonal factor for May is 1.20, means May sales are typically 20% above the average
Factor for July is 0.90, meaning July sales are typically 10% below the average

55. Seasonality & No Trend
Sales Factor Spring /250 = 0.8 Summer /250 = 1.4 Fall /250 = 1.2 Winter /250 = 0.6 Total 1,000 Avg 1,000/4=250

56. Seasonality & No Trend
If we expected total demand for the next year to be 1,100, the average per quarter would be 1,100/4=275 Forecast Spring 275 * 0.8 = 220 Summer 275 * 1.4 = 385 Fall 275 * 1.2 = 330 Winter 275 * 0.6 = 165 Total 1,100

57. Trend & Seasonality Deseasonalize to find the trend
Calculate seasonal factors
Deseasonalize the demand
Find trend of deseasonalized line
Project trend into the future
Project trend line into future
Multiply trend line by seasonal component.

58. Washoe Gaming Win, 1993-96 Looks like a downhill slide
Silver Legacy opened 95Q3
Otherwise, upward trend
Source: Comstock Bank, Survey of Nevada Business & Economics

59. Washoe Win
Definitely a general upward trend, slowed 93-94

62.
Cache
Creek
Thunder
Valley
9/11 CC
Expands

63. Centered Moving Average

64. Deseasonalized

65. 2011 Forecast using 2003-10 SR Data for LR
Seasonal Indexes calculated using data

66. 1. Compute Seasonal Indexes

67. 2. Divide actual by Seasonal Indexes

68. 3.LR on Deseasonalized Data

69. 4.Project Straight Line into Future

70. 5.Multiply Linear line times Indexes

71. How Did We Do? – 2012 Actual Win

72. 1.Compute Seasonal RelativesQ1 Q2 Q3 Q4
2003
240,114,703
259,349,602
279,784,440
246,068,018
2004
231,607,546
259,849,383
297,401,507
259,617,607
2005
245,793,646
269,238,341
294,810,396
257,014,585
2006
245,775,176
269,670,481
294,839,349
257,155,338
2007
244,648,019
273,460,685
284,733,890
246,352,794
2008
227,915,101
237,045,466
258,990,669
206,203,166
2009
190,098,500
211,913,667
217,227,445
185,971,111
2010
187,016,132
198,330,968
209,608,491
175,601,589
2011
174,138,905
192,122,889
203,912,214
175,510,911
avg
220,789,748
241,220,165
260,145,378
223,277,235
236,358,131 SR
0.934
1.021
1.101
0.945

73. 2.Deseasonalize Year Quarter Gaming Win Seasonal Index Deseasonalized
2008 1
190,098,500
0.934
203,502,775 2
211,913,667
1.021
207,642,335 3
217,227,445
1.101
197,364,541 4
185,971,111
0.945
196,866,394
2009
187,016,132
200,203,062
198,330,968
194,333,409
209,608,491
190,442,251
175,601,589
185,889,365

74. 3.LR on Deseasonalized data 2009Q1-2011Q4
Period
Deseasonalized 1
203,502,775 2
207,642,335 3
197,364,541 4
196,866,394 5
200,203,062 6
194,333,409 7
190,442,251 8
185,889,365 9
186,417,833 10
188,250,460 11
185,266,831 12
185,793,374
Intercept = 206,203,550
Slope = -1,954,743
R-squared = 0.848

75. 4.Project trend line into future
Intercept = 206,203,550
Slope = -1,954,743

76. 5.Multiply by Seasonal Relatives

77. How Did We Do? – 2012 Actual Win

78. Summary Calculate indexes Deseasonalize Do a LR
Divide actual demands by seasonal indexes
Do a LR
Project the LR into the future
Seasonalize
Multiply straight-line forecast by indexes