IRAIMay 14

Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning

arXiv:2605.1529935.0
Predicted impact top 88% in IR · last 90 daysOriginality Incremental advance
AI Analysis

For practitioners of multi-stage search/recommendation systems, Fortress offers a method to reduce temporal instability without sacrificing accuracy, though it is validated only on a single domain.

Fortress stabilizes search recommendations by pruning temporally volatile features, improving prediction stability (Coefficient of Variation) and classification performance (PR-AUC) in a large-scale app marketplace.

In search and recommendation systems, predictive models often suffer from temporal instability when certain input features introduce volatility in output scores. This instability can degrade model reliability and user experience especially in multi-stage systems where consistent predictions are critical for downstream decision making. We introduce Fortress, a general framework for enhancing model stability and accuracy by identifying and pruning features that contribute to inconsistent prediction scores over time. Fortress leverages historical snapshots temporally partitioned datasets capturing score fluctuations for the same entity across periods and follows a four-step process: (1) collect historical snapshots, (2) identify samples with unstable predictions, (3) isolate and remove instability-inducing features, and (4) retrain models using only stable features. While semantic features from LLMs and BERT-based models improve generalization, they often lack full query or entity coverage. Engagement-based features offer strong predictive power but tend to introduce temporal instability. Fortress mitigates this trade-off by suppressing the volatility of engagement signals while retaining their predictive value leading to more stable and accurate models. We validate Fortress on a query-to-app relevance model in a large-scale app marketplace. Offline experiments demonstrate notable improvements in prediction stability (measured by Coefficient of Variation) and classification performance (measured by PR-AUC).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes