# Decoupled Recommender Systems: Exploring Alternative Recommender Ecosystem Designs

arXiv: https://arxiv.org/abs/2503.03606 · HTML: https://mlsanity.com/paper/2503.03606/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 5 Mar 2025.

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

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [RecSim: A Configurable Simulation Platform for Recommender Systems](https://mlsanity.com/paper/1909.04847/) (2019)
- [Multisided Fairness for Recommendation](https://mlsanity.com/paper/1707.00093/) (2017)
- [The Unfairness of Popularity Bias in Recommendation](https://mlsanity.com/paper/1907.13286/) (2019)
- [How Bad is Top-K Recommendation under Competing Content Creators?](https://mlsanity.com/paper/2302.01971/) (2023)
- [Multi-FR: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation](https://mlsanity.com/paper/2105.02951/) (2021)
- [Multi-stakeholder Recommendation and its Connection to Multi-sided Fairness](https://mlsanity.com/paper/1907.13158/) (2019)
- [Understanding the growth of the Fediverse through the lens of Mastodon](https://mlsanity.com/paper/2106.15473/) (2021)
- [Understanding Human Intervention in the Platform Economy: A case study of an indie food delivery service](https://mlsanity.com/paper/2303.03523/) (2023)

## Built on by (most cited first, 1 of 1)

- [Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation](https://mlsanity.com/paper/2609.11942/) (2026)

## Abstract (arXiv)

Recommender ecosystems are an emerging subject of research. Such research examines how the characteristics of algorithms, recommendation consumers, and item providers influence system dynamics and long-term outcomes. One architectural possibility that has not yet been widely explored in this line of research is the consequences of a configuration in which recommendation algorithms are decoupled from the platforms they serve. This is sometimes called "the friendly neighborhood algorithm store" or "middleware" model. We are particularly interested in how such architectures might offer a range of different distributions of utility across consumers, providers, and recommendation platforms. In this paper, we create a model of a recommendation ecosystem that incorporates algorithm choice and examine the outcomes of such a design.