# FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems

arXiv: https://arxiv.org/abs/2610.13806 · HTML: https://mlsanity.com/paper/2610.13806/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance](https://mlsanity.com/paper/1905.03151/) (2019)
- [Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams](https://mlsanity.com/paper/2209.01939/) (2022)
- [TransAct V2: Lifelong User Action Sequence Modeling on Pinterest Recommendation](https://mlsanity.com/paper/2506.02267/) (2025)
- [LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest](https://mlsanity.com/paper/2509.03764/) (2025)
- [iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams](https://mlsanity.com/paper/2303.01181/) (2023)
- [Save, Revisit, Retain: A Scalable Framework for Enhancing User Retention in Large-Scale Recommender Systems](https://mlsanity.com/paper/2511.18013/) (2025)
- [Warmer for Less: A Cost-Efficient Strategy for Cold-Start Recommendations at Pinterest](https://mlsanity.com/paper/2512.17277/) (2025)
- [On the Worst-case Communication Overhead for Distributed Data Shuffling](https://mlsanity.com/paper/1609.09823/) (2016)

## Abstract (arXiv)

Production recommender systems have feature-lifecycle asymmetry: adding new features must produce gains on some metric, while feature removal must not regress any metric. In practice, feature deprecation is hard to prioritize as a feature can fail to be removed if it interacts with other features, its importance changes daily, it cannot be evaluated before production models change or data drift occurs, it is in contention for A/B test space with other launches, it causes regressions in an online A/B test, or it is consumed by multiple models that need to coordinate its deprecation. We present FORTE, a model-agnostic production framework for discovering, validating, and removing features. Its efficient perturbation implementation allows daily feature evaluation. To account for interactions, it evaluates candidate feature sets constructed from all the low-rank features through grouped ablation and its offline results are sufficiently predictive of online A/B tests to allow deprecations to proceed to online testing with confidence. Lineage tracing identifies all downstream consumer models to realize the full savings of removing a feature from the training set. We validate FORTE over 2 large-scale recommender systems and find that it identifies deprecable feature sets which do not cause online regressions, while the impact on efficiency depends on model characteristics. On a search-relevance model, FORTE resulted in 3 nested candidate sets of 32, 48, and 59 features. Online guardrails rejected the largest treatment. The 48-feature set was selected for deprecation, removing 43.3% of the model's features. On a large ranking model, FORTE identified 8 candidates for removal. Retraining and A/B testing confirmed no regression. Its launch reduced the trainable parameters by 29.9%, improved serving throughput by 19.8-25.5%, and reduced annual training costs by hundreds of thousands of dollars.