1. Forecasting
OPS 370

2. Forecasting What is Forecasting? Some Thoughts on Forecasts
Determining Future Events Based on Historical Facts and Data
Some Thoughts on Forecasts
Forecasts Tend to Be Wrong!
Forecasts Can Be Biased! (Marketing, Sales, etc.)
Forecasts Tend to Be Better for Near Future
So, Why Forecast?
Better to Have “Educated Guess” About Future Than to Not Forecast At All!
Forecasting - Chapter 4

3. Total Sales, New Offerings
What to Forecast?
Demand for Individual
Products & Services
Short Term
(0-3 Months)
Demand for Product &
Service Families
Medium Term
(3 Months – 2 Years)
Total Sales, New Offerings
Long Term
(>2 Years)
Forecasting - Chapter 4

4. How to Forecast? Qualitative Methods Quantitative Methods
Based On Educated Opinion & Judgment (Subjective)
Particularly Useful When Lacking Numerical Data (Example: Design and Introduction Phases of a Product’s Life Cycle)
Quantitative Methods
Based On Data (Objective)
Forecasting - Chapter 4

5. Qualitative Methods Executive Judgment Sales Force Composite
Market Research/Survey
Delphi Method
Forecasting - Chapter 4

6. Quantitative Methods Time Series & Regression
Time Series  Popular Forecasting Approach in Operations Management
Assumption:
“Patterns” That Occurred in the Past Will Continue to Occur In the Future
Patterns
Random Variation
Trend
Seasonality
Composite
Forecasting - Chapter 4

8. UK Airline Miles Observe: Increasing trend, Seasonal component.
Random variation.
Thousands of Miles

9. Forecasting Steps Collect Relevant/Reliable Data
Data Collection
Collect Relevant/Reliable Data
Be Aware of “Garbage-In, Garbage Out”
Data Analysis
Model Selection
Monitoring
Forecasting - Chapter 4

10. Forecasting Steps Plot the Data Identify Patterns Data Collection
Data Analysis
Model Selection
Monitoring
Forecasting - Chapter 4

11. Forecasting Steps Choose Model Appropriate for Data
Data Collection
Choose Model Appropriate for Data
Consider Complexity Trade-Offs
Perform Forecast(s)
Select Model Based on Performance Measure(s)
Data Analysis
Model Selection
Monitoring
Forecasting - Chapter 4

12. Track Forecast Performance (Conditions May and Often Do Change)
Forecasting Steps
Data Collection
Track Forecast Performance (Conditions May and Often Do Change)
Data Analysis
Model Selection
Monitoring
Forecasting - Chapter 4

13. Time Series Models Short Term Naïve Simple Moving Average
Weighted Moving Average
Exponential Smoothing
Forecasting - Chapter 4

14. Forecasting Example
L&F Bakery has been forecasting by “gut feel.” They would like to use a formal (i.e., quantitative) forecasting technique.
Forecasting - Chapter 4

15. Forecasting Methods Naïve Forecast for July = Actual for June
Ft+1 = At
FJul = AJun = 600
Forecast Very Sensitive to Demand Changes; Good for stable demand
Forecasting - Chapter 4

16. Forecasting Methods
Naïve (Excel)
=C4
=C5
Forecasting - Chapter 4

17. Forecasting Methods Moving Average
Forecast for July = Average of June, May, and April
Ft+1 = (At+At-1+…)/n
FJul = ( )/3 = 500
Values Equally Weighted; Good for stable demand; Sensitive to fluctuation; Lags
Common application: Stock price forecasting

18. Forecasting Methods
30 Day Moving Average of AAPL Price

19. Forecasting Methods Moving Average (Excel) =AVERAGE(C4:C6)

20. Forecasting Methods Moving Average Example Assume n = 2
( )/2 = 150
( )/2 = 162.5
( )/2 = 150
( )/2 = 155

21. Forecasting Methods Weighted Moving Average Ft+1 = (W1At+W2At-1+…)
Assume that W1 = 0.5, W2 =0.3 and W3 = 0.2
FJul = (0.5)(600) + (0.3)(500) + (0.2)(400) = = 530
Typically Gives More Weight to Newer Data
Lags; Sensitive

22. Forecasting Methods Weighted Moving Average =$G$6*C6+$G$5*C5+$G$4*C4

23. Forecasting Methods Weighted Moving Average Example
Assume n = 2, W1 = 0.7, W2 = 0.3
(0.7)(175) + (0.3)(125) = 160
(0.7)(150) + (0.3)(175) = 157.5
(0.7)(150) + (0.3)(150) = 150
(0.7)(160) + (0.3)(150) = 157

24. Forecasting Methods Exponential Smoothing
Forecast for June = Forecast for May + a(Forecast Error in May)
a is a constant between 0 and 1
Forecast Error = Difference Actual Demand and Forecasted Demand
General Formula:
Ft+1 = Ft + aet

25. Forecasting Methods Exponential Smoothing Assume that a = 0.3
What is the forecast for July?
= June Forecast + a(Forecast Error in June) = (0.3)(257) = 420
Requires less data; Good for stable data

26. Forecasting Methods Exponential Smoothing (Excel) Initial forecast
=D4+$G$4*(C4-D4)
=D5+$G$4*(C5-D5)

27. Forecasting Methods Exponential Smoothing Example Assume a = 0.4
Need initial forecast; Assume 125
(125) + (0.4)( ) = 125
(125) + (0.4)( ) = 145
(145) + (0.4)( ) = 147
(147) + (0.4)( ) = 148.2
(148.2) + (0.4)( ) = 152.9

28. Forecasting Methods How to Select Value of a?
Alpha determine importance of recent forecast results in new forecasts
Small alpha  Less importance on recent results (Good for products with stable demand)
Large alpha  Recent forecast results more important (Good for product with varying demands)

29. Determining Forecast Quality
How Well Did a Forecast Perform?
Determine Forecast Error
Error = Actual Demand – Forecasted Demand
Average Error
121.8

30. Determining Forecast Quality
Why is Average Error a Deceiving Measure of Quality?
Better Measures:
Mean Absolute Deviation
Mean Squared Error
Root Mean Squared Error

31. Determining Forecast Quality
Measure of Bias: Tracking Signal = Sum of Errors/MAD
=731/131.8 = 5.55
*OK if between -4 and +4
MAD
MSE

32. Determining Forecast Quality
For this MA(2) forecast. What is MAD, MSE, and TS?

33. Linear Regression
<SKIP Section in Textbook on Exponential Smoothing with Linear Trend>
Linear Regression  Statistical technique that expresses the forecast variable as a linear function of one or more independent variables
Commonly Used for Causal Data
Example: Relationship Between Temperature and Ice Cream Sales
Also Used for Time Series Data (x Variable is Time, y is Demand, Sales, etc.)

34. Linear Trend Line Given Data Parameters to estimate
Y = Values of Response Variable
X = Values of Independent Variable
Parameters to estimate
a = Y-intercept
b = slope
Use “least squares” regression equations to estimate a and b.
Or …

35. Excel for Linear Regression
Use SLOPE Function
Use INTERCEPT Function