# Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

arXiv: https://arxiv.org/abs/2010.00985 · HTML: https://mlsanity.com/paper/2010.00985/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2020.

## Built on by (most cited first, 15 of 15)

- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [Multi-Task Recommendations with Reinforcement Learning](https://mlsanity.com/paper/2302.03328/) (2023)
- [Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation](https://mlsanity.com/paper/2204.06517/) (2022)
- [EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning](https://mlsanity.com/paper/2303.12341/) (2023)
- [Decision-Making Context Interaction Network for Click-Through Rate Prediction](https://mlsanity.com/paper/2301.12402/) (2023)
- [Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce](https://mlsanity.com/paper/2306.05011/) (2023)
- [ConvFormer: Revisiting Transformer for Sequential User Modeling](https://mlsanity.com/paper/2308.02925/) (2023)
- [IA-GCN: Interactive Graph Convolutional Network for Recommendation](https://mlsanity.com/paper/2204.03827/) (2022)
- [AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking](https://mlsanity.com/paper/2310.09706/) (2023)
- [Dynamic Parameterized Network for CTR Prediction](https://mlsanity.com/paper/2111.04983/) (2021)
- [Sequential Search with Off-Policy Reinforcement Learning](https://mlsanity.com/paper/2202.00245/) (2022)
- [Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation](https://mlsanity.com/paper/2509.04154/) (2025)
- [Incorporating Group Prior into Variational Inference for Tail-User Behavior Modeling in CTR Prediction](https://mlsanity.com/paper/2410.15098/) (2024)
- [Multiview graph dual-attention deep learning and contrastive learning for multi-criteria recommender systems](https://mlsanity.com/paper/2502.19271/) (2025)
- [User Representation via Cross Multi-source Behavior Pre-training for Mobile Games](https://mlsanity.com/paper/2609.01057/) (2026)

## Abstract (arXiv)

Click-through rate (CTR) prediction is one of the fundamental tasks for e-commerce search engines. As search becomes more personalized, it is necessary to capture the user interest from rich behavior data. Existing user behavior modeling algorithms develop different attention mechanisms to emphasize query-relevant behaviors and suppress irrelevant ones. Despite being extensively studied, these attentions still suffer from two limitations. First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors. Second, these attentions are usually biased towards frequent behaviors, which is unreasonable since high frequency does not necessarily indicate great importance. To tackle the two limitations, we propose a novel attention mechanism, termed Kalman Filtering Attention (KFAtt), that considers the weighted pooling in attention as a maximum a posteriori (MAP) estimation. By incorporating a priori, KFAtt resorts to global statistics when few user behaviors are relevant. Moreover, a frequency capping mechanism is incorporated to correct the bias towards frequent behaviors. Offline experiments on both benchmark and a 10 billion scale real production dataset, together with an Online A/B test, show that KFAtt outperforms all compared state-of-the-arts. KFAtt has been deployed in the ranking system of a leading e commerce website, serving the main traffic of hundreds of millions of active users everyday.