# Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation

arXiv: https://arxiv.org/abs/2306.03392 · HTML: https://mlsanity.com/paper/2306.03392/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2023.

## Built on by (most cited first, 18 of 18)

- [Generative Regression Based Watch Time Prediction for Short-Video Recommendation](https://mlsanity.com/paper/2412.20211/) (2024)
- [Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation](https://mlsanity.com/paper/2407.12223/) (2024)
- [TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems](https://mlsanity.com/paper/2505.13881/) (2025)
- [Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation](https://mlsanity.com/paper/2508.11086/) (2025)
- [RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems](https://mlsanity.com/paper/2607.29241/) (2026)
- [Learning Cascade Ranking as One Network](https://mlsanity.com/paper/2503.09492/) (2025)
- [Impression-Aware Recommender Systems](https://mlsanity.com/paper/2308.07857/) (2023)
- [Generative Bid Shading in Real-Time Bidding Advertising](https://mlsanity.com/paper/2508.06550/) (2025)
- [RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems](https://mlsanity.com/paper/2602.23012/) (2026)
- [DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression](https://mlsanity.com/paper/2606.07599/) (2026)
- [Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction](https://mlsanity.com/paper/2608.23356/) (2026)
- [Active learning with biased non-response to label requests](https://mlsanity.com/paper/2312.08150/) (2023)
- [LDACP: Long-Delayed Ad Conversions Prediction Model for Bidding Strategy](https://mlsanity.com/paper/2411.16095/) (2024)
- [ACQ: A Deployed Two-Stage Framework for Automated Creative Quota Allocation in Large-Scale Online Advertising](https://mlsanity.com/paper/2412.06167/) (2024)
- [Generate the browsing process for short-video recommendation](https://mlsanity.com/paper/2504.08771/) (2025)
- [Tweedie Regression for Video Recommendation System](https://mlsanity.com/paper/2505.06445/) (2025)
- [FlowTime: Towards Continuous Generative Watch Time Prediction via Flow-based Personalized Priors](https://mlsanity.com/paper/2606.01352/) (2026)
- [PIT-SUN: A Deployable Empirical Marginal Transform Framework with Expectation-Consistent Recovery for Regression in Recommender Systems](https://mlsanity.com/paper/2607.08202/) (2026)

## Abstract (arXiv)

An accurate prediction of watch time has been of vital importance to enhance user engagement in video recommender systems. To achieve this, there are four properties that a watch time prediction framework should satisfy: first, despite its continuous value, watch time is also an ordinal variable and the relative ordering between its values reflects the differences in user preferences. Therefore the ordinal relations should be reflected in watch time predictions. Second, the conditional dependence between the video-watching behaviors should be captured in the model. For instance, one has to watch half of the video before he/she finishes watching the whole video. Third, modeling watch time with a point estimation ignores the fact that models might give results with high uncertainty and this could cause bad cases in recommender systems. Therefore the framework should be aware of prediction uncertainty. Forth, the real-life recommender systems suffer from severe bias amplifications thus an estimation without bias amplification is expected. Therefore we propose TPM for watch time prediction. Specifically, the ordinal ranks of watch time are introduced into TPM and the problem is decomposed into a series of conditional dependent classification tasks which are organized into a tree structure. The expectation of watch time can be generated by traversing the tree and the variance of watch time predictions is explicitly introduced into the objective function as a measurement for uncertainty. Moreover, we illustrate that backdoor adjustment can be seamlessly incorporated into TPM, which alleviates bias amplifications. Extensive offline evaluations have been conducted in public datasets and TPM have been deployed in a real-world video app Kuaishou with over 300 million DAUs. The results indicate that TPM outperforms state-of-the-art approaches and indeed improves video consumption significantly.