Merchandise Recommendation for Retail Events with Word Embedding Weighted Tf-idf and Dynamic Query Expansion
arXiv:2208.08581v17 citationsh-index: 7
Originality Synthesis-oriented
AI Analysis
This work addresses merchandise recommendation for retail events, but it is incremental as it builds on existing tf-idf and word embedding methods.
The paper tackled the problem of recommending merchandise for retail events by improving item retrieval through dynamic query expansion and an enhanced tf-idf formula, resulting in more relevant search rankings.
To recommend relevant merchandises for seasonal retail events, we rely on item retrieval from marketplace inventory. With feedback to expand query scope, we discuss keyword expansion candidate selection using word embedding similarity, and an enhanced tf-idf formula for expanded words in search ranking.