Negative interaction rules boost explainability and performance in recommendation
Evidence Before Sampling: Interpretable Implicit Negative Candidate Discovery for Recommendation
Artificial Intelligence
Summary
Recommender systems suggest items to users based on their interactions, but often there is no clear information about what users dislike. The authors show a way to find which unclicked or unbought items are likely negative examples using clear, interpretable patterns from user behavior. They use these patterns to improve training of recommendation models, making the negative signals explainable and aligned with business goals. This approach improves recommendation accuracy and helps better understand why certain items are treated as negatives.
What this means in practice
- •For ecommerce recommendation teams: Improve recommendation accuracy and interpretability by using evidence-based negative examples derived from user behavior patterns.
- •For advertising optimization teams: Align negative training samples with business goals for better personalized ad targeting and explainable feedback.
Authors
Shreya Rajpal, Sonia Sharma, Swapnil Parekh, Lisa Li, Jeyendran Balakrishnan, Nagaraj Janardhana, Andrew Mattarella-Micke
Abstract
Recommender systems learn from observed user-item interactions, but explicit negative feedback is often unavailable. Since deep learning models require negative signals for training, negative sampling methods typically treat selected unobserved interactions as negatives. However, a missing interaction does not explain why a user is uninterested in an item or whether there is sufficient evidence to label it negative. This is especially important in business recommendation, where negative signals should be interpretable and aligned with business objectives. We formulate implicit negative candidate discovery to identify unobserved interactions supported by observed customer behavior. We encode these patterns as symbolic rules, score them based on support, informativeness, and product relevance, and rank the retained rules by evidence. An LLM then interprets the retained rules using business objectives and domain knowledge; the interpretations are combined with the statistical evidence in the final report. We evaluate our method in an industrial B2B setting and across five public recommendation datasets. Candidate-quality evaluations in the industrial setting and three public datasets show higher precision than the evaluated baselines, while symbolic selection improves downstream test PR-AUC by 12.5% over random selection with four negatives per positive example in the industrial task. Our results show that negative candidate validity can be evaluated separately from downstream recommendation performance. This distinction enables evidence-based, business-aligned, and explainable negative selection, improving both interpretability and model training in sparse, skewed, real-world recommendation settings.