A Knowledge Acquisition System for Price Change Rules

We describe the Knowledge Acquisition System for Price ChangE Rules (KASPER) software system for acquiring knowledge concerning price change rules. The goal is to provide decision rules with high predictive accuracy on unseen data that may explain why a store or brand made a price change in a specific category. These decision rules should relate price changes at one store to those at other stores or brands in the same city. The KASPER approach can use brand-based or distance-based store-to-store relations or use brand-to-brand relations. KASPER was applied to data from four cities to generate decision rules from these relations. We tested the decision rules on unseen data. Our approach was more effective in the two cities where price changes of varied sizes occur than in the two cities where price changes are consistently small.