# Tweedie Regression for Video Recommendation System

arXiv: https://arxiv.org/abs/2505.06445 · HTML: https://mlsanity.com/paper/2505.06445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 9 of 9)

- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation](https://mlsanity.com/paper/2206.06003/) (2022)
- [Autocalibration and Tweedie-dominance for Insurance Pricing with Machine Learning](https://mlsanity.com/paper/2103.03635/) (2021)
- [Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation](https://mlsanity.com/paper/2306.03392/) (2023)
- [Rethinking Multi-Interest Learning for Candidate Matching in Recommender Systems](https://mlsanity.com/paper/2302.14532/) (2023)
- [MISS: Multi-Interest Self-Supervised Learning Framework for Click-Through Rate Prediction](https://mlsanity.com/paper/2111.15068/) (2021)
- [Guess Who Rated This Movie: Identifying Users Through Subspace Clustering](https://mlsanity.com/paper/1408.2055/) (2014)
- [Beyond Labels: Leveraging Deep Learning and LLMs for Content Metadata](https://mlsanity.com/paper/2309.08787/) (2023)
- [Matrix factorization and prediction for high dimensional co-occurrence count data via shared parameter alternating zero inflated Gamma model](https://mlsanity.com/paper/2501.00628/) (2024)

## Abstract (arXiv)

Modern recommendation systems aim to increase click-through rates (CTR) for better user experience, through commonly treating ranking as a classification task focused on predicting CTR. However, there is a gap between this method and the actual objectives of businesses across different sectors. In video recommendation services, the objective of video on demand (VOD) extends beyond merely encouraging clicks, but also guiding users to discover their true interests, leading to increased watch time. And longer users watch time will leads to more revenue through increased chances of presenting online display advertisements. This research addresses the issue by redefining the problem from classification to regression, with a focus on maximizing revenue through user viewing time. Due to the lack of positive labels on recommendation, the study introduces Tweedie Loss Function, which is better suited in this scenario than the traditional mean square error loss. The paper also provides insights on how Tweedie process capture users diverse interests. Our offline simulation and online A/B test revealed that we can substantially enhance our core business objectives: user engagement in terms of viewing time and, consequently, revenue. Additionally, we provide a theoretical comparison between the Tweedie Loss and the commonly employed viewing time weighted Logloss, highlighting why Tweedie Regression stands out as an efficient solution. We further outline a framework for designing a loss function that focuses on a singular objective.