Transcript ppt
Demand and Forecast Dickson K.W. Chiu PhD, SMIEEE Text: Ballou - Business Logistics Management, 5/E (Chapter 8) 1 Learning Objectives To understand some basic concept of demand and forecasting To anticipate typical problems involved in demand and forecasting Dickson Chiu 2006 Demand-2 What’s Forecasted in the Supply Chain Demand, sales or requirements Purchase prices Replenishment and delivery times Dickson Chiu 2006 Demand-3 Some Forecasting Method Choices Historical projection Causal or associative Regression analysis Qualitative Moving average Exponential smoothing Surveys Expert systems or rule-based Collaborative Dickson Chiu 2006 Demand-4 Typical Time Series Patterns: Random 250 Sales 200 150 Actual sales Average sales 100 50 0 0 5 10 15 20 25 Time Dickson Chiu 2006 Demand-5 Typical Time Series Patterns: Random with Trend 250 Sales 200 150 100 Actual sales Average sales 50 0 0 5 10 15 20 25 Time Dickson Chiu 2006 Demand-6 Sales Typical Time Series Patterns: Random with Trend and Seasonal 800 700 600 500 400 300 200 100 0 Actual sales Trend in sales Smoothed trend and seasonal sales 0 10 20 30 40 Time Dickson Chiu 2006 Demand-7 Sales Typical Time Series Patterns: Lumpy Time Dickson Chiu 2006 Demand-8 Is Time Series Pattern Forecastable? Whether a time series can be reasonably forecasted often depends on the time series’ degree of variability. Forecast a regular time series, but use other techniques for lumpy ones. How to tell the difference: A time series is lumpy if X 3 where X mean of the series standard deviation of series, regular, otherwise. Dickson Chiu 2006 Demand-9 Analysis Details See textbook if you are interested Moving Average Exponential Smoothing Formulas Regression Analysis Combined Model Forecasting Note data requirements and timeliness requirement Tracking signal monitors the fit of the model to detect when the model no longer accurately represents the data => events Dickson Chiu 2006 Demand-10 Actions When Forecasting is Inappropriate Seek information directly from customers Collaborate with other channel members Apply forecasting methods with caution (may work where forecast accuracy is not critical) Delay supply response until demand becomes clear Shift demand to other periods for better supply response Develop quick response and flexible supply systems, e.g., order-to-build of Dell Dickson Chiu 2006 Demand-11 Collaborative Forecasting Demand is lumpy or highly uncertain Involves multiple participants each with a unique perspective—“two heads are better than one” Goal is to reduce forecast error The forecasting process is inherently unstable Dickson Chiu 2006 Demand-12 Collaborative Forecasting Key Steps Establish a process champion Identify the needed information and collection processes Establish methods for processing information from multiple sources and the weights assigned to multiple forecasts Create methods for translating forecast into form needed by each party Establish process for revising and updating forecast in real time Create methods for appraising the forecast Show that the benefits of collaborative forecasting are obvious and real Dickson Chiu 2006 Demand-13 Summary Again much domain knowledge is required. Note the data / information requirements and how IT helps to collect / integrate the data for calculations and decision making. Capture forecasting signals (either determined by a business analyst or automatically by a sub-system) as events / exceptions / alerts and forward them to the appropriate system and personnel for decision / action. Collaborative forecasting as well as quick response and flexible supply systems requires much new IT in the process and information integration. Dickson Chiu 2006 Demand-14