Diversity and Serendipity Preference-Aware Recommender System

Diversity and novelty are essential objectives in recommender systems to improve stakeholders' benefits by reducing user's discovery efforts and improving business operators’ sales and revenue. Existing diversity and novelty-based methods indifferently increase diversity or novelty for every user, which inevitably induces the trade-off dilemma between relevance and accuracy. Moreover, different users have different preferences for recommendation diversity and novelty. Such preference should be considered by a recommendation algorithm, thereby avoiding the trade-off dilemma and increasing the prediction accuracy. To address this research gap, we propose a new Diversity and Serendipity-Aware Recommender System (DSPA-RS) problem and its solution method. The MovieLens-2k data are used to evaluate our proposed DSPA-RS method against seven widely used recommendation methods in recommender systems as benchmarks. The test results demonstrate our method shows a superior performance than the benchmarks by a range of 34.30% to 108.27%, indicating that the movies recommended by our method best satisfy users’ diversity and serendipity preference. For recommendation accuracy, our DSPA-RS method outperforms the most accurate method by 34.62% in Precision, 7.71% in Recall, and 24.37% in F1 score. The improvement in recommendation accuracy indicates that DSPA-RS’s consideration and utilization of diversity preference and novelty momentum greatly improves recommendation quality.