HAM: Hybrid Associations Model with Pooling for Sequential Recommendation
We developed a hybrid associations model (HAM) to generate sequential recommendations using two factors: 1) users' long-term preferences and 2) sequential, both high-order and low-order association patterns in the users' most recent purchases/ratings. HAM uses simplistic pooling to represent a set of items in the associations. We compare HAM with three the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings. Our experimental results demonstrate that HAM significantly outperforms the state of the art in all the experimental settings, with an improvement as high as 27.90
READ FULL TEXT