A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
OPEN ACCESS
Loading...
Author / Producer
Date
2023-10-30
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Prediction-based decision-making systems are becoming increasingly prevalent in various domains. Previous studies have demonstrated that such systems are vulnerable to runaway feedback loops, e.g., when police are repeatedly sent back to the same neighborhoods regardless of the actual rate of criminal activity, which exacerbate existing biases. In practice, the automated decisions have dynamic feedback effects on the system itself – which in ML literature is sometimes referred to as performative predictions – that can perpetuate over time, making it difficult for short-sighted design choices to control the system’s evolution. While researchers started proposing longer-term solutions to prevent adverse outcomes (such as bias towards certain groups), these interventions largely depend on ad hoc modeling assumptions and a rigorous theoretical understanding of the feedback dynamics in ML-based decision-making systems is currently missing. In this paper, we use the language of dynamical systems theory, a branch of applied mathematics that deals with the analysis of the interconnection of systems with dynamic behaviors, to rigorously classify the different types of feedback loops in the ML-based decision-making pipeline. By reviewing existing scholarly work, we show that this classification covers many examples discussed in the algorithmic fairness community, thereby providing a unifying and principled framework to study feedback loops. By qualitative analysis, and through a simulation example of recommender systems, we show which specific types of ML biases are affected by each type of feedback loop. We find that the existence of feedback loops in the ML-based decision-making pipeline can perpetuate, reinforce, or even reduce ML biases.
Permanent link
Publication status
published
External links
Editor
Book title
EAAMO '23: Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization
Journal / series
Volume
Pages / Article No.
7
Publisher
Association for Computing Machinery
Event
3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO 2023)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
09478 - Dörfler, Florian / Dörfler, Florian
Notes
Funding
180545 - NCCR Automation (phase I) (SNF)