Log In Sign Up

PURS: Personalized Unexpected Recommender System for Improving User Satisfaction

by   Pan Li, et al.

Classical recommender system methods typically face the filter bubble problem when users only receive recommendations of their familiar items, making them bored and dissatisfied. To address the filter bubble problem, unexpected recommendations have been proposed to recommend items significantly deviating from user's prior expectations and thus surprising them by presenting "fresh" and previously unexplored items to the users. In this paper, we describe a novel Personalized Unexpected Recommender System (PURS) model that incorporates unexpectedness into the recommendation process by providing multi-cluster modeling of user interests in the latent space and personalized unexpectedness via the self-attention mechanism and via selection of an appropriate unexpected activation function. Extensive offline experiments on three real-world datasets illustrate that the proposed PURS model significantly outperforms the state-of-the-art baseline approaches in terms of both accuracy and unexpectedness measures. In addition, we conduct an online A/B test at a major video platform Alibaba-Youku, where our model achieves over 3% increase in the average video view per user metric. The proposed model is in the process of being deployed by the company.


page 1

page 2

page 3

page 4


Latent Unexpected and Useful Recommendation

Providing unexpected recommendations is an important task for recommende...

Latent Unexpected Recommendations

Unexpected recommender system constitutes an important tool to tackle th...

PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest

Latent user representations are widely adopted in the tech industry for ...

Estimating Error and Bias in Offline Evaluation Results

Offline evaluations of recommender systems attempt to estimate users' sa...

Combining Reward and Rank Signals for Slate Recommendation

We consider the problem of slate recommendation, where the recommender s...

A Scalable Probabilistic Model for Reward Optimizing Slate Recommendation

We introduce Probabilistic Rank and Reward model (PRR), a scalable proba...

User-controllable Recommendation Against Filter Bubbles

Recommender systems usually face the issue of filter bubbles: overrecomm...