Module 9 Forecasting

1
Module 9 - Forecasting
2
Course Framework

• 1. Cost
• - Design Selection
• 2. Quality
• - TQM
• - SQC
• 3. Speed
• - Project Management
• - Supply Chain

• 4. Flexibility
• - Inventory
• - Location
• - Forecasting
• - Aggregate Planning

3
Learning Objectives

• 1. Identify common principles of forecasting
• 2. Identify types of forecasting methods and
  their characteristics
• 3. Generate time series forecasts
• 4. Compute forecast accuracy
• 5. Explain model selection

4
1. Principles of Forecasting

• Forecasts are rarely perfect
• Forecasts are more accurate for grouped data than
  for individual items
• Forecast are more accurate for shorter than
  longer time periods

5
2. Types of Forecasting Models

• Qualitative methods
• Forecasts generated subjectively by the
  forecaster
• Quantitative methods
• Forecasts generated through mathematical modeling

6
Qualitative Methods
7
Qualitative Methods
8
Qualitative Methods
9
Quantitative Methods

• Time Series Models
• Assumes the future will follow same patterns as
  the past
• Causal Models
• Explores cause-and-effect relationships
• Uses leading indicators to predict the future
• E.g., housing starts and appliance sales

10
3. Time Series Data Composition

• Data historic pattern random variation
• Historic pattern to be forecasted
• Level (long-term average)
• Trend
• Seasonality
• Cycle
• Random Variation cannot be predicted

11
Time Series Patterns
12
Time Series Patterns
13
Time Series Patterns
14
Time Series Patterns
15
Time Series Models

• Naive Ft1 At
• The forecast is equal to the actual value
  observed during the last period good for level
  patterns
• Simple Mean Ft1 S At / n
• The average of all available data - good for
  level patterns
• Moving Average Ft1 S At / n
• The average value over a set time period (e.g.
  the last four weeks)
• Each new forecast drops the oldest data point
  adds a new observation
• More responsive to a trend but still lags behind
  actual data

16
Time Series Models (continued)

• Weighted Moving Average Ft1 S CtAt
• All weights must add to 1.00
• e.g. Ct .5, Ct-1 .3, Ct-2 .2
• Allows emphasizing one period over others above
  indicates more weight on recent data (Ct.5)
• Differs from the simple moving average that
  weighs all periods equally - more responsive to
  trends

17
Time Series Models (continued)

• Exponential Smoothing Ft1 aAt (1-a)Ft
• Most frequently used time series method because
  of ease of use and minimal amount of data needed
• Need just three pieces of data to start
• Last periods forecast (Ft)
• Last periods actual value (At)
• Select value of smoothing coefficient, a, between
  0 and 1.0
• Higher a values (e.g. .7 or .8) may place too
  much weight on last periods random variation

18
Time Series Problem

• Determine F8
• 2-period MA
• 4-period MA
• 2-period WMA
• (0.6) At-1 and (0.4) At-2
• Exponential smoothing
• a 0.2 and F7 372

19
View Data
?
20
Computation and Solution
21
Computation and Solution
22
Computation and Solution
23
Computation and Solution
24
Computation and Solution
25
Computation and Solution
26
Averaging causes smoothing
27
Measuring Forecast Error

• Forecasts are never perfect
• Need to know how much we should rely on our
  chosen forecasting method
• Measuring forecast error
• Et Ft - At

28
4. Measuring Forecasting Accuracy
29
Choice Example
30
Choice Example
31
Choice Example
32
Choice Example
33
Choice Example
34
Control?
35
Control?
36
Control?
37
Control?
38
5. Selecting a Forecasting Model

• The amount type of available data
• Some methods require more data than others
• Degree of accuracy required
• Increasing accuracy means more data
• Length of forecast horizon
• Different models for 3 month vs. 10 years
• Presence of data patterns
• Lagging will occur when a forecasting model meant
  for a level pattern is applied with a trend