Papers › Deep Interest Network for Click-Through Rate Prediction

Deep Interest Network for Click-Through Rate Prediction

21 Jun 2017arXiv:1706.06978archive 2025-07-28

Guorui Zhou, Chengru Song, Xiaoqiang Zhu, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, Kun Gai

Click-through rate prediction is an essential task in industrial applications, such as online advertising. Recently deep learning based models have been proposed, which follow a similar Embedding&MLP paradigm. In these methods large scale sparse input features are first mapped into low dimensional embedding vectors, and then transformed into fixed-length vectors in a group-wise manner, finally concatenated together to fed into a multilayer perceptron (MLP) to learn the nonlinear relations among features. In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are. The use of fixed-length vector will be a bottleneck, which brings difficulty for Embedding&MLP methods to capture user's diverse interests effectively from rich historical behaviors. In this paper, we propose a novel model: Deep Interest Network (DIN) which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad. This representation vector varies over different ads, improving the expressive ability of model greatly. Besides, we develop two techniques: mini-batch aware regularization and data adaptive activation function which can help training industrial deep networks with hundreds of millions of parameters. Experiments on two public datasets as well as an Alibaba real production dataset with over 2 billion samples demonstrate the effectiveness of proposed approaches, which achieve superior performance compared with state-of-the-art methods. DIN now has been successfully deployed in the online display advertising system in Alibaba, serving the main traffic.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

18 repositories listed; official and paper-mentioned ones first.

zhougr1993/DeepInterestNetwork officialmentioned in papermentioned on GitHubtf report
GitHub-HongweiZhang/prediction-flow mentioned on GitHubpytorchMIT report
StephenBo-China/DIEN-DIN mentioned on GitHubtf report
UlionTse/mlgb mentioned on GitHubpytorch report
YafeiWu/DIEN mentioned on GitHubtf report
imvishvaraj/ctr_nlp mentioned on GitHub report
johnlevi/recsys mentioned on GitHub report
massquantity/LibRecommender mentioned on GitHubtfMIT report
searchlink/din mentioned on GitHubtf report
shenweichen/DeepCTR mentioned on GitHubtf report
shenweichen/DeepCTR-Torch mentioned on GitHubpytorchApache-2.0 report
tangxyw/RecAlgorithm mentioned on GitHubtfBSD-2-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Click-Through Rate PredictionPrediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Click-Through Rate Prediction Amazon DIN + Dice Activation AUC 0.8871 #1 of 5 Archive leaderboard report
Click-Through Rate Prediction Amazon DIN AUC 0.8818 #2 of 5 Archive leaderboard report
Click-Through Rate Prediction MovieLens 20M DIN + Dice Activation AUC 0.7348 #2 of 6 Archive leaderboard report
Click-Through Rate Prediction MovieLens 20M DIN AUC 0.7337 #3 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections