Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Business
Automatic Identification Of Time Series Features For Rule-Based Forecasting, Monica Adya, Fred Collopy, J. Scott Armstrong, Miles Kennedy
Automatic Identification Of Time Series Features For Rule-Based Forecasting, Monica Adya, Fred Collopy, J. Scott Armstrong, Miles Kennedy
Monica Adya
Rule-based forecasting (RBF) is an expert system that uses features of time series to select and weight extrapolation techniques. Thus, it is dependent upon the identification of features of the time series. Judgmental coding of these features is expensive and the reliability of the ratings is modest. We developed and automated heuristics to detect six features that had previously been judgmentally identified in RBF: outliers, level shifts, change in basic trend, unstable recent trend, unusual last observation, and functional form. These heuristics rely on simple statistics such as first differences and regression estimates. In general, there was agreement between automated …
Rule Based Forecasting [Rbf] - Improving Efficacy Of Judgmental Forecasts Using Simplified Expert Rules, Monica Adya, Edward J. Lusk
Rule Based Forecasting [Rbf] - Improving Efficacy Of Judgmental Forecasts Using Simplified Expert Rules, Monica Adya, Edward J. Lusk
Monica Adya
Rule-based Forecasting (RBF) has emerged to be an effective forecasting model compared to well-accepted benchmarks. However, the original RBF model, introduced in1992, incorporates 99 production rules and is, therefore, difficult to apply judgmentally. In this research study, we present a core rule-set from RBF that can be used to inform both judgmental forecasting practice and pedagogy. The simplified rule-set, called coreRBF, is validated by asking forecasters to judgmentally apply the rules to time series forecasting tasks. Results demonstrate that forecasting accuracy from judgmental use of coreRBF is not statistically different from that reported from similar applications of RBF. Further, we …