Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2309.14046

Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience

Sangeet Jaiswal·Korah T Malayil·Saif Jawaid·Sreekanth Vempati
View original source ↗Read source document ↗Export metadata ↓

Abstract

In the realm of e-commerce, popular platforms utilize widgets to recommend advertisements and products to their users. However, the prevalence of mobile device usage on these platforms introduces a unique challenge due to the limited screen real estate available. Consequently, the positioning of relevant widgets becomes pivotal in capturing and maintaining customer engagement. Given the restricted screen size of mobile devices, widgets placed at the top of the interface are more prominently displayed and thus attract greater user attention. Conversely, widgets positioned further down the page require users to scroll, resulting in reduced visibility and subsequent lower impression rates. Therefore it becomes imperative to place relevant widgets on top. However, selecting relevant widgets to display is a challenging task as the widgets can be heterogeneous, widgets can be introduced or removed at any given time from the platform. In this work, we model the vertical widget reordering as a contextual multi-arm bandit problem with delayed batch feedback. The objective is to rank the vertical widgets in a personalized manner. We present a two-stage ranking framework that combines contextual bandits with a diversity layer to improve the overall ranking. We demonstrate its effectiveness through offline and online A/B results, conducted on proprietary data from Myntra, a major fashion e-commerce platform in India.

Explore related subjects

cs.IRcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Sangeet Jaiswal, Korah T Malayil, Saif Jawaid, Sreekanth Vempati. 2023-09-25. Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience. https://arxiv.org/abs/2309.14046

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

WebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks

Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsing, underrepresent research-oriented environments and scholarly discovery workflows, and often depend on live sites whose changing content and structure undermine reproducibility. arXiv provides a realistic, reproducible, hierarchically structured, information-centric testbed without privacy-sensitive interactions. We introduce WebArxiv, a static-snapshot benchmark comprising 510 time-invariant tasks, each with a unique deterministic ground truth. Its diverse, realistic scholarly tasks go beyond simple information lookup and rule following to emphasize multi-constraint paper retrieval, fine-grained content extraction, and cross-paper comparison. Evaluations of a range of foundation-model-based web agents show that WebArxiv remains challenging. Behavioral analysis reveals that agents over-rely on fixed interaction histories, causing incomplete or repetitive reasoning. We therefore equip agents with a lightweight dynamic-memory mechanism for adaptive retrieval and reasoning over relevant context. The benchmark and code are available at https://anonymous.4open.science/r/74E4423BVNW/README.md.

cs.IR↗
arXiv2026

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval benchmark derived from, and complementing GreekBarBench, which did not include retrieval. The new benchmark comprises 283 bar-exam questions, each accompanied by the facts of the case it refers to, and 6,308 candidate statutory articles to retrieve from. Questions and facts are stated in everyday language, but need to be mapped to the formal terminology of statutes and their abstract legal concepts. A further complication is that not all of the case facts are relevant to each question of a case. Experimenting with three BM25 variants and nine dense retrievers, we find that vanilla dense retrieval far outperforms vanilla sparse retrieval in Recall@100. However, LLM-based query reformulation helps BM25 close that gap, while also improving dense retrieval. With a ten-round ReAct-like LLM reformulation loop that we introduce, BM25 improves further in Recall@100 and obtains the best nDCG and MAP scores of all tested retrievers. Query reformulation also outperforms pseudo-relevance feedback, sparse-dense fusion, and English translation.

cs.IR↗
arXiv2026

Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant

We study a parameterized hybrid ranker that fuses a dense embedding list and a sparse lexical list. The method has a small, explicit parameter vector: a dense prior $α\in [0,1]$, a score-versus-rank mix $λ\in [0,1]$, an RRF smoothing parameter $κ> 0$, optional list-geometry coefficients that move $α$ per query, and a router margin $τ$ that can turn sparse search off. We grid-search those ranges on SciFact train (809 queries) and freeze the chosen values on SciFact test (300). The tuned rank-score mix ($α= 0.8$, $λ= 0.75$, $κ= 20$) reaches 0.753 nDCG@10 and 0.889 recall@10, outperforming dense BGE (0.742 / 0.871) and equal-weight RRF (0.707 nDCG@10) on that test split. A list-conditioned $α$ adds +0.0006 nDCG; a sparse-off router is rejected by the same train split (any $τ$ that skipped approximately 50% of queries lost nDCG). These coefficients are dataset-specific. Equal RRF with the same models does not beat dense on a nine-zip BEIR macro-average (0.479 vs. 0.519 nDCG@10). Repeating the same train-then-freeze sweep independently on all 20 indexed units beats equal RRF on 20/20 and dense on 16/20 (unit-mean nDCG@10 0.467 vs. 0.462 dense vs. 0.420 RRF). Other corpora should reuse the ranges, not a copy of the SciFact point.

cs.IR↗