# Click-Through Rate Prediction with the User Memory Network

arXiv: https://arxiv.org/abs/1907.04667 · HTML: https://mlsanity.com/paper/1907.04667/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Click-Through Rate Prediction in Online Advertising: A Literature Review](https://mlsanity.com/paper/2202.10462/) (2022)
- [User Response Prediction in Online Advertising](https://mlsanity.com/paper/2101.02342/) (2021)
- [Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction](https://mlsanity.com/paper/2105.08909/) (2021)
- [CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies](https://mlsanity.com/paper/2408.12004/) (2024)
- [Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Training](https://mlsanity.com/paper/2309.15881/) (2023)

## Abstract (arXiv)

Click-through rate (CTR) prediction is a critical task in online advertising systems. Models like Deep Neural Networks (DNNs) are simple but stateless. They consider each target ad independently and cannot directly extract useful information contained in users' historical ad impressions and clicks. In contrast, models like Recurrent Neural Networks (RNNs) are stateful but complex. They model temporal dependency between users' sequential behaviors and can achieve improved prediction performance than DNNs. However, both the offline training and online prediction process of RNNs are much more complex and time-consuming. In this paper, we propose Memory Augmented DNN (MA-DNN) for practical CTR prediction services. In particular, we create two external memory vectors for each user, memorizing high-level abstractions of what a user possibly likes and dislikes. The proposed MA-DNN achieves a good compromise between DNN and RNN. It is as simple as DNN, but has certain ability to exploit useful information contained in users' historical behaviors as RNN. Both offline and online experiments demonstrate the effectiveness of MA-DNN for practical CTR prediction services. Actually, the memory component can be augmented to other models as well (e.g., the Wide&Deep model).