A combination of simple models by forward predictor selection for job recommendation

Abstract

The present paper introduces a solution for the RecSys Challenge 2016. The principle of the proposed technique is to define various models capturing the specificity of the dataset and then to subsequently find the optimal combinations of these by considering different user categories. The approach follows a practical way for the fine-tuning of recommender algorithms, highlighting their components, training-and prediction time. Based on forward predictor selection, it can be shown that item-neighbor methods and the recommendation of already shown or interacted items have great potential in improving the offline accuracy. The best composition consists of 11 predictor instances that achieved the third place with 665,592 leaderboard score and 2,005,263 final score.