Papers for

e commerce platform engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Flow based method improves personalized recommendation accuracy

SourceFlow: Collaborative Source Coupling for Flow-Based Recommendation

Abstract: Diffusion-based recommenders learn user preferences by denoising interaction histories, but the added noise can distort the original preference signals. Flow-based collaborative filtering (CF) instead learns a discrete path from a sampled source to the user's observed training interactions (the target history), enabling inference in a few steps. Existing flow-based CF methods sample sources using global item frequencies to reflect the sparsity and popularity of observed interactions. Each source is sampled independently of its target history, leaving the predictor without user-specific source cues for learning to reconstruct that history. We propose SourceFlow, which brings collaborative structure into the source distribution itself rather than adding further conditioning to the predictor. Like inference from observed histories, training uses collaborative evidence to predict missing interactions. Specifically, Neighborhood Coupling constructs displaced binary sources by replacing historical items with unobserved collaborative alternatives. Collaborative Consensus further refines replacement probabilities using evidence from other interactions of users who share the observed item. Stretched Restoration retains these replacements at late flow times during training, providing more opportunities to recover the original interactions. Experiments on five recommendation datasets show consistent improvements over competitive baselines, including a mean relative Recall@10 gain of 15.7% over the strongest flow-based baseline. Controlled experiments confirm that these gains depend on correctly pairing collaborative sources with their target histories, as reassigning the same source vectors across users reverses the gains. Code will be publicly released upon acceptance.

Tue 3 NovInformation Retrieval
The gist
Recommendation systems try to predict what you might like by looking at your past choices, but the noise added in some methods can hide your true preferences. The authors propose SourceFlow, a technique that better guesses missing favorite items by using patterns from similar users' interactions. This method replaces some past choices with related guesses based on shared tastes, making it easier for the model to learn and recover the original preferences. Tests across multiple datasets show this approach gives more accurate recommendations than previous flow-based methods.
Open → 2611.04455v1

Personalized cross domain models improve sequential recommendations

Bezier-Guided Adaptive Flow for Cross-domain Sequential Recommendation

Abstract: Cross-domain sequential recommendation aims to alleviate data sparsity and cold-start problems by transferring useful preference knowledge across domains. However, users exhibit varying degrees of preference consistency across domains, while existing methods often rely on global alignment objectives or coarse-grained transfer strategies. Such approaches may introduce irrelevant information and provide limited flexibility in adapting semantic representations to individual user preferences. To address these challenges, we propose BGAFlow, a personalized framework that combines state-adaptive semantic evolution with user-specific transfer control. BGAFlow first establishes a shared semantic space through unified dual-domain pretraining with user profiles inferred by a large language model (LLM). Based on latent interest overlap, it then estimates a personalized horizon to determine the appropriate transfer extent for each user. To enable semantic adaptation, BGAFlow constructs a conditional Bezier curve as a geometric reference and learns a residual flow that progressively refines the trajectory based on intermediate preference states. The learned flow incorporates dynamic preference feedback to adjust transfer directions, while recommendation supervision and trajectory regularization encourage effective and smooth adaptation. Extensive experiments on real-world datasets demonstrate that BGAFlow consistently outperforms state-of-the-art baselines, validating the benefits of personalized transfer control and state-adaptive semantic evolution.

Thu 22 OctInformation Retrieval
The gist
When people use different websites or apps, it can be hard for systems to recommend things they like because their preferences vary. The authors created a way to better share preference information between different domains like shopping and movies but adjusted for each person’s unique interests. They do this by using smart techniques to map and adapt preferences along a smooth path tailored to each user. Their approach helps recommendation systems learn and update more effectively, leading to better suggestions in multiple areas.
Open → 2610.30825v1

Time aware rotary position embedding improves recommendation accuracy

T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation

Abstract: Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation along with design choices made for text, including Rotary Position Embedding (RoPE). In language models, RoPE encodes token indices for relative position reasoning, but in recommendation, an interaction index records only event order, saying nothing about elapsed time, behavioral cycles across scales, or calendar phase. We revisit this choice and propose T-RoPE, a time-aware RoPE for sequential generative recommendation that replaces index-only rotation with timestamp-based angles, learnable temporal coefficients, multiscale frequency banks, shifted query alignment, and non-stationary key rotation. We prove that standard RoPE, even on timestamps, remains time-translation invariant and cannot distinguish seasonal contexts, and that T-RoPE breaks this invariance while preserving the RoPE interface. Across five public benchmarks, T-RoPE achieves the best result on every metric on every dataset, improving over the strongest baseline by 78--130\% in HR@10 on the sparse PixelRec data and 8--12\% across metrics on Amazon Books. On an industrial-scale e-commerce dataset with more than 6B interactions, it improves every metric over the HSTU + Time RAB backbone by 13--82\%, with ablations attributing the largest gains to multiscale frequencies ($+56\%$ NDCG@50) and non-stationary keys ($+4\%$). An online A/B test in the Shop app yields positive lifts in conversion rate ($+0.33\%$) and order count ($+0.63\%$). We also provide forward and backward algorithms whose added cost is linear in sequence length and head dimension, keeping time-aware RoPE practical for large generative recommenders.

Thu 24 SeptArtificial IntelligenceInformation RetrievalMachine Learning
The gist
Recommendation systems that suggest items like products or content often rely on the order of previous interactions but ignore the exact timing between them. The authors noticed that using only the order misses important signals like how much time passed or seasonal patterns. They created T-RoPE, a method that adds timing information to better understand user behavior. This improved recommendation accuracy on several datasets and even showed small but positive effects in a real online shopping app.
Open → 2609.30576v1