Reproduce “Retail Product Search: A Practical Approach at Target” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Darshan Sonagara, Qujiaheng Zhang, Ankit Singh, Alex Li
For example, the query “yoge mat” returns a Yoga Mat 3mm Teal, illustrating wording gaps rather than proving performance. Target runs lexical and vector retrieval together, filters vector candidates for attributes, and merges both lists. In four-week tests, the hybrid raised click-through rate 0.97%, order conversion 0.98%, and demand per visitor 1.10% versus lexical-only search; this establishes package-level effects, not component causality.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.