In this paper we present a time-based genre prediction strategy that can inform the book recommendation process. To explicitly consider time in predicting genres of interest, we rely on a popular time series forecasting model as well as reading patterns of each individual reader or group of readers (in case of libraries or publishing companies). Based on a conducted initial assessment using the Amazon dataset, we demonstrate our strategy outperforms its baseline counter-part.
This document was originally published in Proceedings of the Poster Track of the 10th ACM Conference on Recommender Systems, RecSys 2016 by CEUR-WS. Copyright restrictions may apply.
Dragovic, Nevena and Pera, Maria Soledad. (2016). "Genre Prediction to Inform the Recommendation Process". Proceedings of the Poster Track of the 10th ACM Conference on Recommender Systems, RecSys 2016, 1688.