Track: Retail Operations
Titel: Predictably unpredictable: How judgmental forecasts and machine learning predictions complement each other
Zusammenfassung: We propose a three-step demand forecasting framework that combines the expert’s knowledge of the market with machine learning algorithm’s ability to leverage historical information to forecast seasonal demand for rapid innovation products. Using data from Canyon Bicycles, we find an 28% reduction in forecast error over a purely judgmental forecast.