Article ID: | iaor19931238 |
Country: | United States |
Volume: | 38 |
Issue: | 10 |
Start Page Number: | 1394 |
End Page Number: | 1414 |
Publication Date: | Oct 1992 |
Journal: | Management Science |
Authors: | Armstrong J. Scott, Collopy Fred |
Keywords: | forecasting: applications, artificial intelligence: expert systems |
This paper examines the feasibility of rule-based forecasting, a procedure that applies forecasting expertise and domain knowledge to produce forecasts according to features of the data. The authors developed a rule base to make annual extrapolation forecasts for economic and demographic time series. The development of the rule base drew upon protocol analyses of five experts on forecasting methods. This rule base, consisting of 99 rules, combined forecasts from four extrapolation methods (the random walk, regression, Brown’s linear exponential smoothing, and Holt’s exponential smoothing) according to rules using 18 features of time series. For one-year ahead