# Personalized Bundle List Recommendation

## TL;DR

This paper introduces a novel bundle generation network (BGN) for personalized product bundle recommendation, combining quality and diversity through DPPs, and demonstrates significant improvements over existing methods across multiple datasets.

## Contribution

The paper proposes a new BGN model that integrates feature-aware softmax, masked beam search, and DPPs for high-quality, diverse bundle recommendations, advancing the state-of-the-art.

## Key findings

- BGN outperforms existing methods in quality and diversity.
- BGN achieves 3.85x faster response time.
- Improves precision by 16% on average.

## Abstract

Product bundling, offering a combination of items to customers, is one of the marketing strategies commonly used in online e-commerce and offline retailers. A high-quality bundle generalizes frequent items of interest, and diversity across bundles boosts the user-experience and eventually increases transaction volume. In this paper, we formalize the personalized bundle list recommendation as a structured prediction problem and propose a bundle generation network (BGN), which decomposes the problem into quality/diversity parts by the determinantal point processes (DPPs). BGN uses a typical encoder-decoder framework with a proposed feature-aware softmax to alleviate the inadequate representation of traditional softmax, and integrates the masked beam search and DPP selection to produce high-quality and diversified bundle list with an appropriate bundle size. We conduct extensive experiments on three public datasets and one industrial dataset, including two generated from co-purchase records and the other two extracted from real-world online bundle services. BGN significantly outperforms the state-of-the-art methods in terms of quality, diversity and response time over all datasets. In particular, BGN improves the precision of the best competitors by 16\% on average while maintaining the highest diversity on four datasets, and yields a 3.85x improvement of response time over the best competitors in the bundle list recommendation problem.