# TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation

arXiv: https://arxiv.org/abs/2506.02267 · HTML: https://mlsanity.com/paper/2506.02267/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 18 of 18)

- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Wide & Deep Learning for Recommender Systems](https://mlsanity.com/paper/1606.07792/) (2016)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [Behavior Sequence Transformer for E-commerce Recommendation in Alibaba](https://mlsanity.com/paper/1905.06874/) (2019)
- [Liger Kernel: Efficient Triton Kernels for LLM Training](https://mlsanity.com/paper/2410.10989/) (2024)
- [User Behavior Retrieval for Click-Through Rate Prediction](https://mlsanity.com/paper/2005.14171/) (2020)
- [TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou](https://mlsanity.com/paper/2302.02352/) (2023)
- [Cut Your Losses in Large-Vocabulary Language Models](https://mlsanity.com/paper/2411.09009/) (2024)
- [TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest](https://mlsanity.com/paper/2306.00248/) (2023)
- [TWIN V2: Scaling Ultra-Long User Behavior Sequence Modeling for Enhanced CTR Prediction at Kuaishou](https://mlsanity.com/paper/2407.16357/) (2024)
- [Rethinking Personalized Ranking at Pinterest: An End-to-End Approach](https://mlsanity.com/paper/2209.08435/) (2022)
- [LiRank: Industrial Large Scale Ranking Models at LinkedIn](https://mlsanity.com/paper/2402.06859/) (2024)
- [Trinity: Syncretizing Multi-/Long-tail/Long-term Interests All in One](https://mlsanity.com/paper/2402.02842/) (2024)
- [Efficient user history modeling with amortized inference for deep learning recommendation models](https://mlsanity.com/paper/2412.06924/) (2024)
- [Beyond Item Dissimilarities: Diversifying by Intent in Recommender Systems](https://mlsanity.com/paper/2405.12327/) (2024)
- [Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention](https://mlsanity.com/paper/2409.15373/) (2024)

## Built on by (most cited first, 9 of 9)

- [LLaTTE: Scaling Laws for Multi-Stage Sequence Modeling in Large-Scale Ads Recommendation](https://mlsanity.com/paper/2601.20083/) (2026)
- [UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale](https://mlsanity.com/paper/2606.00422/) (2026)
- [Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation](https://mlsanity.com/paper/2511.06077/) (2025)
- [Long-Term Embeddings for Balanced Personalization](https://mlsanity.com/paper/2604.08181/) (2026)
- [PRAGMA: Revolut Foundation Model](https://mlsanity.com/paper/2604.08649/) (2026)
- [Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems](https://mlsanity.com/paper/2607.19357/) (2026)
- [SequenceO1: End-to-End Ultra-Long (100K) Sequence Modeling in Recommendation with Low-Rank Caching](https://mlsanity.com/paper/2609.08443/) (2026)
- [DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation](https://mlsanity.com/paper/2609.32215/) (2026)
- [FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems](https://mlsanity.com/paper/2610.13806/) (2026)

## Abstract (arXiv)

Modeling user action sequences has become a popular focus in industrial recommendation system research, particularly for Click-Through Rate (CTR) prediction tasks. However, industry-scale CTR models often rely on short user sequences, limiting their ability to capture long-term behavior. Additionally, these models typically lack an integrated action-prediction task within a point-wise ranking framework, reducing their predictive power. They also rarely address the infrastructure challenges involved in efficiently serving large-scale sequential models. In this paper, we introduce TransAct V2, a production model for Pinterest's Homefeed ranking system, featuring three key innovations: (1) leveraging very long user sequences to improve CTR predictions, (2) integrating a Next Action Loss function for enhanced user action forecasting, and (3) employing scalable, low-latency deployment solutions tailored to handle the computational demands of extended user action sequences.