Deep-learning Causal Retrieval Optimization for Efficient e-commerce Distribution in Pinterest

• URL: http://arxiv.org/abs/2607.14161v2
• Date: Tue, 21 Jul 2026 03:28:01 GMT
• Title: Deep-learning Causal Retrieval Optimization for Efficient e-commerce Distribution in Pinterest
• Abstract summary: We deploy a production system at Pinterest that learns personalized and contextualized triggering policies.<n>A deep multi-task model jointly predicts outcomes and uplift of multiple events.<n>A linear-time offline replay is designed to select thresholds and forecast policy impact.
• Score: 0.7827524915894094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pinterest is where people turn inspiration into action as users browse ideas, then take steps toward realization, often by discovering shoppable content. To support this journey, we must distribute commerce content when it helps, not when it distracts. We frame this as a causal decision of triggering shopping candidate generators in early retrieval and deploy a production system at Pinterest that learns personalized and contextualized triggering policies. A deep multi-task model jointly predicts outcomes and uplift of multiple events, trained with a doubly-robust pseudo-outcome alongside calibrated outcome losses for stable, single-robust uplift learning. A randomized data logging supplies counterfactual coverage, and the model is evaluated by both regular and reverse metrics for full assessment. A linear-time offline replay is designed to select thresholds and forecast policy impact with extremely high consistency with online results. For productionization, the model runs in parallel with remote retrieval calls without end-to-end latency regression. At web scale, we cut shopping triggers by up to 85% while holding key shopping sessions neutral, improving important total sessions (+0.26%) and Pin saves (+1.10%), with significant infrastructure savings. By unifying deep causal learning with reliable offline replay and demonstrating production-grade deployment, this work provides a generally practical recipe for early-retrieval optimizations in modern cascading recommenders beyond shopping, aligning exploration and cost with user intent at scale.

Related papers

• From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation [1.8192758370546824]
  We present a decision-centric framework that instead optimize causal effects under global constraints.<n>We evaluate it with offline simulations on a public bandit dataset, targeted architectural ablations, and an online A/B test on LinkedIn Feed marketing traffic.<n>The end-to-end treatment policy delivered a statistically significant $+7.20%$ lift in the primary long-term-value metric.
  arXiv  Detail & Related papers  (2026-08-10T19:54:08Z)
• Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion [52.722575491987904]
  We show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios.<n>We prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load.
  arXiv  Detail & Related papers  (2026-07-15T21:17:42Z)
• CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search [16.32525191514382]
  We present CoRe, a system that redeployed weekly for over five months in a major short-video search engine.<n>Our reward uses the deployed multimodal relevance model as its source and a multiplicative ratio form mirroring the production fusion algebra.<n>A semi-online Mixed Preference Optimization loop makes this reward affordable at multi-million-instance weekly scale.
  arXiv  Detail & Related papers  (2026-06-12T05:19:40Z)
• Modelling Customer Trajectories with Reinforcement Learning for Practical Retail Insights [6.143744262581817]
  Heuristics such as the Travelling Salesman Problem (TSP) are commonly used as inexpensive approximations.<n>Actual trajectories deviate by an average of 28% from shortest paths, highlighting a tradeoff between accuracy and practicality.<n>We propose an agent-based modelling framework that casts trajectory prediction as maximum entropy reinforcement learning.
  arXiv  Detail & Related papers  (2026-05-18T14:17:51Z)
• Action-Aware Generative Sequence Modeling for Short Video Recommendation [50.74467504063892]
  Short videos often contain diverse segments, and users may not hold the same attitude toward all of them.<n>Traditional binary-classification recommendation models, which treat a video as a single holistic entity, face limitations in accurately capturing such nuanced preferences.<n>We propose a novel modeling paradigm: Action-Aware Generative Sequence Network (A2Gen), which refines user actions along the temporal dimension.
  arXiv  Detail & Related papers  (2026-04-28T16:41:04Z)
• SPARC: Soft Probabilistic Adaptive multi-interest Retrieval Model via Codebooks for recommender system [0.0]
  Current multi-interest retrieval methods pose three major challenges.<n>Online inference typically employs an over-exploited strategy.<n>We propose a novel retrieval framework named "Soft Probabilistic Adaptive Retrieval Model via Codebooks"
  arXiv  Detail & Related papers  (2025-08-12T17:16:37Z)
• Reinforcement Learning with Action Chunking [56.66655947239018]
  We present Q-chunking, a recipe for improving reinforcement learning algorithms for long-horizon, sparse-reward tasks.<n>Our recipe is designed for the offline-to-online RL setting, where the goal is to leverage an offline prior dataset to maximize the sample-efficiency of online learning.<n>Our experimental results demonstrate that Q-chunking exhibits strong offline performance and online sample efficiency, outperforming prior best offline-to-online methods on a range of long-horizon, sparse-reward manipulation tasks.
  arXiv  Detail & Related papers  (2025-07-10T17:48:03Z)
• Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning [90.23629291067763]
  A promising approach for improving reasoning in large language models is to use process reward models (PRMs) PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward models (ORMs) To improve a base policy by running search against a PRM or using it as dense rewards for reinforcement learning (RL), we ask: "How should we design process rewards?" We theoretically characterize the set of good provers and our results show that optimizing process rewards from such provers improves exploration during test-time search and online RL.
  arXiv  Detail & Related papers  (2024-10-10T17:31:23Z)
• Continuous Attribution of Episodical Outcomes for More Efficient and Targeted Online Measurement [4.361526134899724]
  We apply Causal Surrogacy to model a long-term outcome using leading indicators that are incrementally observed. Applying this approach to the guest booking metric at Airbnb resulted in significant variance reductions of 50% to 85%.
  arXiv  Detail & Related papers  (2022-10-28T19:20:20Z)
• Approaching sales forecasting using recurrent neural networks and transformers [57.43518732385863]
  We develop three alternatives to tackle the problem of forecasting the customer sales at day/store/item level using deep learning techniques. Our empirical results show how good performance can be achieved by using a simple sequence to sequence architecture with minimal data preprocessing effort. The proposed solution achieves a RMSLE of around 0.54, which is competitive with other more specific solutions to the problem proposed in the Kaggle competition.
  arXiv  Detail & Related papers  (2022-04-16T12:03:52Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.