# Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation

Source: [Memento: Personalized RAG-Style Long-Retention Data Scaling for META Ads Recommendation](<https://www.sota2.com/research/paper/6a152906dbd7150506f7de0f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-27T05:00:05.520Z

Authors: Xiaoyu Chen, Ruichen Wang, Jieming Di, Suofei Feng, Nafis Abrar, Lilly Kumari, Tony Tsui, Yilin Liu, Yu Lu, Sowmya Patapati, Junwei Xiong, Qiao Yang, Dorothy Sun, Yang Cao, Victor Chen, Pan Chen, Ramsundar Sundarkumar, Shivendra Pratap Singh, Arnold Overwijk, Ling Leng, Dinesh Ramasamy, Sri Reddy, Robert Malkin, Sandeep Pandey

Published: 2026-05-22T00:12:38.000Z

## Abstract

Modeling of long history data suffers from long-context window attention dilution, system efficiency and catastrophic forgetting problems, where naive linear scaling approach like LastN would fail. We introduce Memento, a personalized retrieval-augmented framework that treats historical user engagements as a document corpus and ad requests as queries, retrieving relevant interactions via Maximal Marginal Relevance (MMR) to balance similarity with diversity. We identify two complementary applications: Representation Memento, which retrieves historical embeddings for feature augmentation, and Data Memento, which retrieves past training examples for multipass training. Through infrastructure co-design -- temporal chunking, INT8 quantization, and asynchronous serving -- Memento achieves 5-10$\\times$ resource efficiency over linear scaling. Memento processes daily requests with sub-10ms latency, yielding 0.25-0.3% Normalized Entropy gain on both click-through and conversion prediction. In production, Memento delivers a 1% CTR lift on Facebook Feed and Reels and a 1.2% CVR lift, scaling personalization to 365+ days of history.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [CTR Prediction on Internal Production Advertising Dataset](<https://www.sota2.com/research/sota/ctr-prediction-on-internal-production-advertising-dataset.md>): CTR Prediction; Internal Production Advertising Dataset; CTR N.E.: -0.25.

- [CVR Prediction on Internal Production Advertising Dataset](<https://www.sota2.com/research/sota/cvr-prediction-on-internal-production-advertising-dataset.md>): CVR prediction; Internal Production Advertising Dataset; CVR Relative Error: -0.26.

- [Conversion Rate Prediction on Production CVR Model Data 150+ day V0 (Evaluation)](<https://www.sota2.com/research/sota/conversion-rate-prediction-on-production-cvr-model-data-150-plus-day-v0-evaluation.md>): Conversion Rate Prediction; Production CVR Model Data 150+ day V0 (Evaluation); Normalized Error (Eval): -0.195.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.24051>)

[PDF](<https://arxiv.org/pdf/2605.24051.pdf>)