@mschuber

Personalized Diagnosis and Repair of Customer Requirements in Constraint-based Recommendation

, , , , and . DX-09 - 20th International Workshop on Principles of Diagnosis, page 315--320. (2009)

Abstract

Constraint-based recommender applications derive interesting products and services from large and potentially complex item sets. If such applications cannot find a solution, repair actions are proposed that provide support for getting out of the so-called “no solution could be found” dilemma. Such repairs are not personalized and thus often cause a low level of satisfaction and cancellations of sessions. In this work we introduce a personalized repair algorithm that integrates the concepts of model-based diagnosis with collaborative recommendation approaches. For demonstration purposes, we present the results of a study that show improvements in prediction accuracy when personalized repair actions are proposed.

Links and resources

Tags