审计Transformer模型在交易中的算法偏见，发现其偏好低频价格数据。
Auditing Algorithmic Bias in Transformer-Based Trading
- 用基于部分信息分解的指标量化每种资产对决策的影响
- 模型完全忽略价格波动性，偏好低频价格变动数据
- 适合关注金融AI公平性与决策可解释性的研究者
Transformer模型在金融领域应用日益广泛，但其潜在的风险和偏见仍缺乏深入研究。本文旨在审计模型在决策中对波动性数据的依赖程度，并量化价格变动频率对模型预测置信度的影响。我们采用Transformer模型进行预测，并引入基于部分信息分解（PID）的指标，衡量每种资产对模型决策的贡献。分析揭示两个关键发现：第一，模型完全忽视数据波动性；第二，模型存在偏向于低频价格变动数据的偏见。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。