# Towards Reliable Recommender Systems for Rating Data

arXiv: https://arxiv.org/abs/2412.20802 · HTML: https://mlsanity.com/paper/2412.20802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 59 references that are in the map.
- First posted on arXiv 30 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms](https://mlsanity.com/paper/2011.01731/) (2020)
- [Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares](https://mlsanity.com/paper/1410.2596/) (2014)
- [A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research](https://mlsanity.com/paper/1911.07698/) (2019)
- [Manipulating Recommender Systems: A Survey of Poisoning Attacks and Countermeasures](https://mlsanity.com/paper/2404.14942/) (2024)
- [A Comprehensive Review of Recommender Systems: Transitioning from Theory to Practice](https://mlsanity.com/paper/2407.13699/) (2024)
- [Matrix Completion When Missing Is Not at Random and Its Applications in Causal Panel Data Models](https://mlsanity.com/paper/2308.02364/) (2023)
- [Interpretable Matrix Completion: A Discrete Optimization Approach](https://mlsanity.com/paper/1812.06647/) (2018)
- [Robust Matrix Completion with Heavy-tailed Noise](https://mlsanity.com/paper/2206.04276/) (2022)
- [Dynamic Matrix Recovery](https://mlsanity.com/paper/2305.10524/) (2023)
- [When Respondents Don't Care Anymore: Identifying the Onset of Careless Responding](https://mlsanity.com/paper/2303.07167/) (2023)
- [Robust Estimation and Inference with Categorical Data](https://mlsanity.com/paper/2403.11954/) (2024)
- [Robust Estimation of Polychoric Correlation](https://mlsanity.com/paper/2407.18835/) (2024)

## Abstract (arXiv)

Recommender systems are widely used in the digital landscape to match users with content fitting their preferences. However, growing concerns about fake accounts, strategic manipulation, and other deceptive online behavior place increasing pressure on the reliability of these systems. A common statistical approach behind recommender systems is so-called matrix completion, which predicts how users would rate items they have not yet consumed based on patterns in observed ratings. Realistically applying matrix completion methods requires jointly addressing several overlooked challenges: (i) ratings on discrete scales (such as 1--5 stars); (ii) the presence of malicious users who deliberately manipulate the system to their advantage through fake profiles; (iii) ratings missing not at random since users are more likely to consume items they expect to like; and (iv) fostering transparency, reproducibility, and stability. We jointly address these challenges by proposing a novel method, Robust Discrete Matrix Completion (RDMC), designed to capture the key characteristics of sparse rating data while remaining reliable in the presence of manipulation. We evaluate RDMC through two case studies and carefully designed simulation experiments. Our work thereby offers a statistically-sound blueprint for future studies on how to evaluate recommender systems under realistic scenarios.