# Auditing Algorithmic Bias in Transformer-Based Trading

arXiv: https://arxiv.org/abs/2510.05140 · HTML: https://mlsanity.com/paper/2510.05140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 8 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Novel Approach to the Partial Information Decomposition](https://mlsanity.com/paper/1908.08642/) (2019)
- [Quantformer: from attention to profit with a quantitative transformer trading strategy](https://mlsanity.com/paper/2404.00424/) (2024)
- [RoFormer for Position Aware Multiple Instance Learning in Whole Slide Image Classification](https://mlsanity.com/paper/2310.01924/) (2023)
- [Trading Under Uncertainty: A Distribution-Based Strategy for Futures Markets Using FutureQuant Transformer](https://mlsanity.com/paper/2505.05595/) (2025)

## Abstract (arXiv)

Transformer models have become increasingly popular in financial applications, yet their potential risk making and biases remain under-explored. The purpose of this work is to audit the reliance of the model on volatile data for decision-making, and quantify how the frequency of price movements affects the model's prediction confidence. We employ a transformer model for prediction, and introduce a metric based on Partial Information Decomposition (PID) to measure the influence of each asset on the model's decision making. Our analysis reveals two key observations: first, the model disregards data volatility entirely, and second, it is biased toward data with lower-frequency price movements.