Auditing Algorithmic Bias in Transformer-Based Trading
By: Armin Gerami, Ramani Duraiswami
Potential Business Impact:
Finds money-predicting computer favors slow-moving prices.
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.
Similar Papers
Partial multivariate transformer as a tool for cryptocurrencies time series prediction
Statistical Finance
Predicts crypto prices better, but doesn't guarantee profit.
Predicting Stock Movement with BERTweet and Transformers
Machine Learning (CS)
Helps predict stock prices using Twitter.
Data-Efficient Realized Volatility Forecasting with Vision Transformers
Machine Learning (CS)
Helps predict stock price changes using past data.