Forecasting: Practice and Process for Demand Management (with CD-ROM) - Hardcover

Hans Levenbach starts his career at AT&T Bell Laboratories as an applied statistician, participating in forecasting project and developing analytical support systems for the Bell Operating Companies. Over the years he has many years of teaching experience as Adjunct Professor in the Business Schools of Columbia University and New York University. In 1996, he was a Visiting Professor at the Stern School of Business at NYU. In his professional life, he served as President, Treasurer and Board member of the International Institute of Forecasters (IIF). In June 2003 he was elected Fellow of the IIF. Hans graduated from Acadia University (Canada) with a degree in Physics and Mathematics, and received an MSc in Electrical Engineering from Queen's University (Canada) and an M.A. and Ph.D. in Mathematical Statistics from the University of Toronto. Hans is involved in all aspects of the company and particularly enjoys working with forecasting practitioners and software developers.

James P. Cleary held a number of leadership positions in marketing and finance at AT&T, Lucent Technologies, Avaya, and New York Telephone Company. Recently, he developed market sizing and quantified business case value propositions that demonstrated the product benefits from the perspectives of the end users, the service providers and the manufacturer. He directed the business management functions of strategic planning, business planning, forecasting and results analysis. He also led a forecast improvement team that improved the accuracy of the customer team demand forecasts. He was the Director-Market Research & Analysis in the Business Communications Services unit. His financial positions included the CFO-Data Communications Services and CFO-Computer Systems. Mr. Cleary developed courses in time series and econometric modeling for AT&T. He also developed a course for managers of the forecasting function.

Part I: INTRODUCING THE FORECASTING PROCESS. 1. Forecasting as a Structured Process. Inside the Crystal Ball. Is Forecasting Worthwhile? Creating a Structured Forecasting Process. Establishing an Effective Demand Forecasting Strategy. Summary. References. Problems. Useful Reading. Cases. 2. Classifying Forecasting Techniques. Selecting a Forecasting Technique. A Life Cycle Perspective. Market Research. New Product Introductions. Promotions and Special Events. Sales Force Composites and Customer Collaboration. Neural Nets for Forecasting. The Prototypical Forecasting Application: Projecting Historical Patterns. Computer Study: How to Forecast with Weighted Averages. Summary. References. Problems. Useful Reading. Cases. Part II: EXPLORING TIME SERIES. 3. Data Exploration for Forecasting. Exploring Data. Creating Data Summaries. Displaying Data Summaries. Serially Correlated Data. What Does Normality Have to Do with It? The Need for Nontraditional Methods. Summary. References. Problems. Useful Reading. Cases. Appendix A: The Need for Robustness in Correlation. Appendix B: Comparing Estimation Techniques. 4. Characteristics of Time Series. Visualizing Components in a Time Series. A First Look at Trend and Seasonality. What is Stationarity? Classifying Trends. Computer Study: How to Detect Trends. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Appendix A: A Two-Way Table Decomposition. 5. Assessing Accuracy of Forecasts. The Need to Measure Forecast Accuracy. Ways to Evaluate Accuracy. Measures of Forecast Accuracy. Comparing with Naive Techniques. Tracking Tools. Computer Study: How to Monitor Forecasts. Summary. References. Problems. Useful Reading. Cases. Part III: FORECASTING THE AGGREGATE. 6. Dealing with Seasonal Fluctuations. Seasonal Influences. The Ratio-to-Moving Average Method. Additive and Multiplicative Seasonal Decompositions. Census Seasonal Adjustment Method. Resistant Smoothing. Computer Study: How to Detect Seasonal Cycles-Formalwear Rental Revenue. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. 7. Forecasting the Business Environment. Forecasting with Economic Indicators. Trend-Cycle Forecasting with Turning Points. Using Elasticities. Econometrics and Business Forecasting. Computer Study: Using "Pressures" to Analyze Business Cycles. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Part IV: APPLYING BOTTOM-UP TECHNIQUES. 8. The Exponential Smoothing Method. What is Exponential Smoothing? Smoothing Weights. Types of Smoothing Techniques. Smoothing Levels and Constant Change. Damped and Exponential Trends. Seasonal Models. Handling Special Events with Smoothing Models. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Appendix. 9. Disaggregate Product-Demand Forecasting. Forecasting for the Supply Chain. A Framework for an Integrated Demand Forecasting System. Automated Statistical Forecasting. Disaggregate Product-Demand Forecasting Checklist. Computer Study: How to Create a Time-Phased Replenishment Plan. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Part V: FORECASTING WITH CAUSAL FORECASTING MODELS. 10. Creating and Analyzing Causal Forecasting Models. A Model Building Strategy. What are Regression Models? Creating Multiple Linear Regression Models. Learning from Residual Patterns. Validating Preliminary Modeling Assumptions. Computer Study: How to Forecast with Transformed Data. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Appendix: Achieving Linearity. 11. Linear Regression Analysis. Graphing Relationships. Creating and Interpreting Output. Making Inferences about Model Parameters. Autocorrelation Correction. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. 12. Forecasting with Regression Models. Multiple Linear Regression Analysis. Assessing Model Adequacy. Selecting Variables. Indicators for Qualitative Variables. Analyzing Residuals. The Need for Robustness in Regression. Multiple Regression Checklist. Computer Study: How to Forecast with Qualitative Variables. Summary. References. Computer Exercises. Useful Reading. Cases. Part VI: FORECASTING WITH ARIMA MODELS. 13. Building ARIMA Models: The Box-Jenkins Approach. Why Use ARIMA Models for Forecasting? The Linear Filter Model as A Black Box. A Model Building Strategy. Identification: Interpreting ACF and PACF. Identifying Nonseasonal ARIMA Models. Estimation: Fitting Models to Data. Diagnostic Checking: Validating Model Adequacy. Implementing Nonseasonal ARIMA Models. Identifying Seasonal ARIMA Models. Implementing Seasonal ARIMA Models. ARIMA Modeling Checklist. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. 14. Forecasting with ARIMA Models. ARIMA Models for Forecasting. Models for Forecasting Stationary Time Series. Models for Nonstationary Time Series. Seasonal ARIMA Models. Forecast Probability Limits. ARIMA Forecasting Checklist. Summary. References. Problems. Computer Exercises. Useful Reading. Cases. Appendix A: Expressing ARIMA Models in Compact Form. Appendix B: Forecast Error and Forecast Variance for ARIMA Models. Part VII: IMPROVING FORECASTING EFFECTIVENESS. 15. Selecting the Final Forecast Number. Preparing Forecast Scenarios. Establishing Credibility. Using Forecasting Simulations. Designing Forecasting Simulations. Reconciling Sales Force and Customer Inputs. Gaining Acceptance from Management. The Forecaster's Checklist. Summary. References. Case. Useful Reading. Cases. 16. Implementing the Forecasting Process. PEERing into the Future. A Framework for Process Improvement. An Implementation Checklist. Using "Virtual" Forecasting Services. The Forecasting Manager's Checklists. Summary. References. Useful Reading. Cases. Glossary.