Building an Interpretable Recommender via Loss-Preserving Transformation
This addresses the need for interpretable personalization in online content and promotions, though it appears incremental as it adapts existing methods to handle specific cost structures.
The paper tackles the problem of building an interpretable recommender system with custom misclassification costs that depend on both recommendations and customers, by proposing a loss-preserving transformation method that allows the use of standard interpretable classification algorithms while minimizing the custom cost function.
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses. Unlike in a standard multi-class classification setting, misclassification costs depend on both recommended actions and customers. Our method transforms such a data set to a new set which can be used with standard interpretable multi-class classification algorithms. The transformation has the desirable property that minimizing the standard misclassification penalty in this new space is equivalent to minimizing the custom cost function.