Suchen und Finden
Service
Business Forecasting - Practical Problems and Solutions
Michael Gilliland, Len Tashman, Udo Sglavo
Verlag Wiley, 2015
ISBN 9781119228271 , 416 Seiten
Format PDF, ePUB, OL
Kopierschutz DRM
Business Forecasting
7
Contents
13
Foreword
17
Preface
21
Chapter 1 Fundamental Considerations in Business Forecasting
23
1.1 Getting Real about Uncertainty (Paul Goodwin)
25
Avoiding Jail
26
Point versus Probabilistic Forecasts
26
Is it Worth Communicating Uncertainty?
28
Limitations of Probabilistic Forecasts
28
What Is the Best Way to Convey Uncertainty?
29
Estimating Uncertainty
29
Conclusions
30
REFERENCES
30
1.2 What Demand Planners Can Learn from the Stock Market (Charles K. Re Corr)
31
Why Forecast the Future Market
32
What Makes Any Forecast Useful?
33
Some Errors Are More Forgiving than Others
35
1.3 Toward a More Precise Definition of Forecastability (John Boylan)
36
Stability versus Forecastability
36
Defining Forecastability in Terms of Forecast Error
37
Upper Bound of a Forecasting Error Metric
38
Lower Bound of a Forecasting Error Measure
39
Finding More Forecastable Series
41
Conclusions
43
REFERENCES
43
1.4 Forecastability: A New Method for Benchmarking and Driving Improvement (Sean Schubert)
44
Introduction: Establishing Comparability
44
What Is Forecastability?
45
Forecastability DNA
46
Building a Model of Forecastability
48
The Forecastability Model in Action
51
Conclusions
57
REFERENCES
57
1.5 Forecast Errors and Their Avoidability (Steve Morlidge)
58
Beginnings
59
Defining Success in Forecasting
59
Creating a Metric
60
What the Experts Say
61
Avoidability
62
The Way Forward: A Conjecture
63
The Unavoidability Ratio
63
The Empirical Evidence
65
The Next Step
67
REFERENCES
67
1.6 The Perils of Benchmarking (Michael Gilliland)
68
Danger, Danger
68
1.7 Can We Obtain Valid Benchmarks from Published Surveys of Forecast Accuracy? (Stephan Kolassa)
70
Introduction
71
Published Surveys of Forecast Accuracy
71
What Is a Benchmark?
76
Problems with Forecast Accuracy Surveys
76
External vs. Internal Benchmarks
80
REFERENCES
81
1.8 Defining “Demand” for Demand Forecasting (Michael Gilliland)
82
Introduction: Unconstrained vs. Constrained Demand
83
Orders vs. True Demand
83
Shipments and Sales vs. True Demand
84
Seeking an Operational Definition of True Demand
85
True vs. Constrained Forecasts
87
Assessing Forecast Accuracy and Making Financial Projections
88
REFERENCES
88
1.9 Using Forecasting to Steer the Business: Six Principles (Steve Morlidge)
89
Economic Forecasting Is Broken
89
The Narrow Focus of the Forecasting Profession
90
Prescription for Change
92
Forecasting to Steer the Business: Six Principles
94
Conclusions
97
REFERENCES
98
1.10 The Beauty of Forecasting (David Orrell)
98
Introduction
99
Perfect Model
99
Economy at Risk
100
Lessons from Business Forecasting
101
REFERENCES
102
Chapter 2 Methods of Statistical Forecasting
103
2.1 Confessions of a Pragmatic Forecaster (Chris Chatfield)
104
Introduction
105
Some History
105
Forecasting Methods
107
Which Method Is Best?
110
Implementation of Forecasting Methods
111
Publication Bias
112
Experience in Consulting
112
REFERENCES
113
2.2 New Evidence on the Value of Combining Forecasts (Paul Goodwin)
114
Forecast Combination and the Bank of England’s Suite of Statistical Forecasting Models
114
Why Did Combining Work?
115
Trimmed Means
116
Conclusions
117
REFERENCES
117
2.3 How to Forecast Data Containing Outliers (Eric Stellwagen)
117
Option #1: Outlier Correction
118
Option #2: Separate the Demand Streams
119
Option #3: Use a Forecasting Method that Models the Outliers
120
Summary
120
2.4 Selecting Your Statistical Forecasting Level (Eric Stellwagen)
120
Can It Be Simpler?
121
Do You Have Enough Structure?
122
Are the Relationships Between Levels Changing in Time?
123
Summary
124
2.5 When Is a Flat-line Forecast Appropriate? (Eric Stellwagen)
124
2.6 Forecasting by Time Compression (Udo Sglavo)
126
Introduction
127
The Challenge
127
Approach 1: Traditional Forecasting
128
Approach 2: Forecasting by Time Compression
129
Conclusion
132
Acknowledgments
132
REFERENCES
134
2.7 Data Mining for Forecasting: An Introduction (Chip Wells and Tim Rey)
134
Introduction, Value Proposition, and Prerequisites
134
Big Data in Data Mining for Forecasting
136
NOTES
140
REFERENCES
141
2.8 Process and Methods for Data Mining for Forecasting (Chip Wells and Tim Rey)
142
Time-Series Data Creation
143
Two Phases of Data Mining for Forecasting
144
Three Methods for Data Mining in Time Series
145
NOTE
148
REFERENCES
148
2.9 Worst-Case Scenarios in Forecasting: How Bad Can Things Get? (Roy Batchelor)
148
Introduction
149
A Standard View of New Car Sales
150
Time-Varying Volatility in Car Sales
153
Concluding Remarks
154
Appendix: The GARCH Model
156
2.10 Good Patterns, Bad Patterns (Roy Batchelor)
157
Introduction
157
Good Patterns
158
Bad Patterns
159
Conclusion
162
REFERENCES
163
Chapter 3 Forecasting Performance Evaluation and Reporting
165
3.1 Dos and Don’ts of Forecast Accuracy Measurement: A Tutorial (Len Tashman)
166
The Most Basic Issue: Distinguish In-Sample Fit from Out-of-Sample Accuracy
167
Assessing Forecast Accuracy
168
Accuracy Metrics
172
Benchmarking and Forecastability
177
Costs of Forecast Error
179
REFERENCES
181
3.2 How to Track Forecast Accuracy to Guide Forecast Process Improvement (Jim Hoover)
182
Introduction
182
Obstacles to Tracking Accuracy
183
Multistep Tracking Process
183
Conclusions and Recommendations
191
REFERENCES
191
3.3 A “Softer” Approach to the Measurement of Forecast Accuracy (John Boylan)
192
The Complement of Mean Absolute Percent Error
192
Forecast Researchers and Practitioners: Different Needs and Perspectives
193
The Soft Systems Approach
194
Relevant Systems and Root Definitions
195
Effectiveness Measures and Accuracy Measures
195
Using a Structured Approach in Practice
197
Postscript: Advice on the Complement of MAPE
198
REFERENCES
198
3.4 Measuring Forecast Accuracy (Rob Hyndman)
199
Training and Test Sets
199
Forecast Accuracy Measures
200
Time-Series Cross-Validation
203
Conclusions
206
REFERENCES
206
3.5 Should We Define Forecast Error as e = F - A or e = A - F? (Kesten Green and Len Tashman)
206
The Issue
207
The Survey
207
Support for A – F
208
Support for F – A
209
3.6 Percentage Error: What Denominator? (Kesten Green and Len Tashman)
210
The Issue
210
Survey Results
211
REFERENCES
216
3.7 Percentage Errors Can Ruin Your Day (Stephan Kolassa and Roland Martin)
217
Introduction
218
Rolling Dice
219
Variants of the APE
221
Alternatives to the APE and Its Variants
224
Conclusion
225
REFERENCES
225
3.8 Another Look at Forecast-Accuracy Metrics for Intermittent Demand (Rob Hyndman)
226
Introduction: Three Ways to Generate Forecasts
227
An Example of What Can Go Wrong
228
Measurement of Forecast Errors
229
REFERENCES
233
3.9 Advantages of the MAD/Mean Ratio over the MAPE (Stephan Kolassa and Wolfgang Schütz)
233
The MAD, the MAPE, and the MAD/Mean
234
The MAD/Mean Ratio as a Weighted MAPE
235
The Issue of Forecast Bias
236
The MASE
237
The Case of Intermittent Series
238
Recap
239
REFERENCES
239
3.10 Use Scaled Errors Instead of Percentage Errors in Forecast Evaluations (Lauge Valentin)
239
Evaluating Forecasts in the LEGO Group
240
Problems with Percentage Errors
241
Scaled Errors
243
The GMASE
245
The Problem of Bad Forecasts
246
Perspectives for Intercompany Benchmarking
247
How to Make MASE and GMASE Management Friendly
248
Summary
249
REFERENCES
249
3.11 An Expanded Prediction-Realization Diagram for Assessing Forecast Errors (Roy Pearson)
250
Introduction
250
The Prediction-Realization Plot
250
The 17 Possible Outcomes
252
Predicted Changes vs. Predicted Levels
252
Applying the PRD to Energy Price Forecasts
253
Payroll Employment Forecasts: The Difficulty of Improvingon a Naïve Forecast
255
Summary and Recommendation
259
REFERENCES
259
3.12 Forecast Error Measures: Critical Review and Practical Recommendations (Andrey Davydenko and Robert Fildes)
260
1. Introduction
260
2. Data
261
3. Critical Review of Existing Measures
262
4. Recommended Scheme for Measuring the Accuracy of Point Forecasts across Many Series
268
5. Results of Empirical Evaluation
269
6. Conclusions
270
REFERENCES
271
3.13 Measuring the Quality of Intermittent Demand Forecasts: It’s Worse than We’ve Thought! (Steve Morlidge)
272
Introduction
272
The Problems with Intermittent Demand
273
The Numerator Problem
274
Solutions to the Numerator Problem
275
The Bias-Adjusted Error
278
Conclusion
279
Appendix
280
REFERENCES
280
3.14 Managing Forecasts by Exception (Eric Stellwagen)
281
What Is an Exception Report?
281
How Do I Select the Thresholds?
283
3.15 Using Process Behavior Charts to Improve Forecasting and Decision Making (Martin Joseph and Alec Finney)
284
Introduction
285
Data to Information to Insight
285
Control Limits to Distinguish Signals from Noise
288
Application of PBCs to Forecasting
292
Applying PBCs for Decision Making
293
Bringing PBCs into S&OP and Other Planning Activities
295
REFERENCES
297
3.16 Can Your Forecast Beat the Naïve Forecast? (Shaun Snapp)
298
Background
298
What to Expect?
298
How Long Should You Test the Naïve Forecast Against the Current Live Forecast?
299
System Implications
300
Conclusion
300
REFERENCES
301
Chapter 4 Process and Politics of Business Forecasting
303
4.1 FVA: A Reality Check on Forecasting Practices (Michael Gilliland)
304
Introduction
305
Calculating Forecast Value Added
305
How Organizations Are Using FVA
307
Which Naïve Model to Use?
309
A Reality Check on Forecasting Practices
310
REFERENCE
310
4.2 Where Should the Forecasting Function Reside? (Larry Lapide)
310
Executing an Effective Forecasting Process
312
Evaluation Criteria
312
The Pros and Cons of Departments
313
Conclusion
315
4.3 Setting Forecasting Performance Objectives (Michael Gilliland)
316
Five Steps for Setting Forecasting Performance Objectives
317
REFERENCES
318
4.4 Using Relative Error Metrics to Improve Forecast Quality in the Supply Chain (Steve Morlidge)
319
Introduction
319
Background
320
The Practical Challenge
322
Focus the Efforts
322
Devise Improvement Strategies
324
Setting Realistic Targets
327
Conclusion
330
REFERENCES
330
4.5 Why Should I Trust Your Forecasts? (M. Sinan Gönül, Dilek Önkal, and Paul Goodwin)
331
Introduction
331
Trust and Forecasting
331
The Determinants of Trust
332
Trust and Adjustments to Provided Forecasts
334
The Need for Open Communication Channels
334
Working to Earn Trust
335
REFERENCES
336
4.6 High on Complexity, Low on Evidence: Are Advanced Forecasting Methods Always as Good as They Seem? (Paul Goodwin)
337
The Complexity Love Affair
337
A Case in Point
338
Proper Testing of Accuracy
338
Inadequate Evidence
339
Conclusions
340
REFERENCES
340
4.7 Should the Forecasting Process Eliminate Face-to-Face Meetings? (J. Scott Armstrong)
341
Introduction
341
The Wisdom of Crowds
341
Face-to-Face Meetings Could Be Effective
342
The Case Against Face-to-Face Meetings
343
Alternatives to Face-to-Face Meetings: Markets, Nominal Groups, and Virtual Teams
344
A Prediction Case
346
Are Face-to-Face Meetings Useful Under Some Conditions?
347
Action Steps
347
Conclusions
348
REFERENCES
348
4.8 The Impact of Sales Forecast Game Playing on Supply Chains (John Mello)
349
Introduction
350
The Nature of Supply Chains
350
Games People Play
351
Consequences for the Supply Chain
354
Conditions Fostering Game Playing
357
How to Control Game Playing
359
Conclusion
361
REFERENCES
361
4.9 Role of the Sales Force in Forecasting (Michael Gilliland)
362
Three Assumptions About Salespeople
362
Gathering Sales Force Input
363
Can Salespeople Forecast Their Customers’ Behavior?
365
Can You Trust the Forecast from a Salesperson?
365
Compensation as an Incentive for Honesty
366
Does Improving Customer Level Forecasts Always Matter?
368
Commitments Are Not Forecasts
369
Conclusions
369
NOTES
370
REFERENCES
370
4.10 Good and Bad Judgment in Forecasting: Lessons from Four Companies (Robert Fildes and Paul Goodwin)
371
Introduction
371
Adjustments Galore
372
The Illusion of Control
374
When Do Adjustments Improve Accuracy and When Do TheyNot?
374
The Importance of Definitions
377
History Is Not Bunk
378
Conclusions
379
REFERENCES
379
4.11 Worst Practices in New Product Forecasting (Michael Gilliland)
380
Unrealistic Accuracy Expectations
381
Reverse Engineering the Forecast
382
Cherry-Picking Analogies
382
Insisting on a Wiggle
383
The Hold-and-Roll
384
Ignoring the Product Portfolio
384
Using Inappropriate Methods
385
REFERENCES
385
4.12 Sales and Operations Planning in the Retail Industry (Jack Harwell)
385
Sales and Operations Planning
387
Three Plans
387
Three Levels
389
Sales and Operations Planning Escalation Process
391
Other Keys to S&OP Success
391
Goals and Key Performance Indicators
393
Top-Level Support
393
Conclusion
394
4.13 Sales and Operations Planning: Where Is It Going? (Tom Wallace)
394
Summary
401
REFERENCE
401
About the Editors
403
Index
405
EULA
417