{"ID":2862343,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.05140","arxiv_id":"2510.05140","title":"Auditing Algorithmic Bias in Transformer-Based Trading","abstract":"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.","short_abstract":"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 pred...","url_abs":"https://arxiv.org/abs/2510.05140","url_pdf":"https://arxiv.org/pdf/2510.05140v2","authors":"[\"Armin Gerami\",\"Ramani Duraiswami\"]","published":"2025-10-01T21:20:26Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CE\"]","methods":"[\"Transformer\"]","has_code":false}