Alternative Loss Function in Evaluation of Transformer Models

TL;DR

This paper introduces the Mean Absolute Directional Loss (MADL) function for evaluating transformer models in finance, demonstrating its effectiveness over LSTM models through empirical experiments on assets.

Contribution

It proposes a new loss function, MADL, tailored for financial forecasting, and shows its superiority in optimizing transformer models over LSTMs.

Findings

Transformers outperform LSTMs in financial forecasting tasks.

MADL improves model optimization for quantitative finance.

Empirical results confirm the effectiveness of MADL in real-world data.

Abstract

The proper design and architecture of testing machine learning models, especially in their application to quantitative finance problems, is crucial. The most important aspect of this process is selecting an adequate loss function for training, validation, estimation purposes, and hyperparameter tuning. Therefore, in this research, through empirical experiments on equity and cryptocurrency assets, we apply the Mean Absolute Directional Loss (MADL) function, which is more adequate for optimizing forecast-generating models used in algorithmic investment strategies. The MADL function results are compared between Transformer and LSTM models, and we show that in almost every case, Transformer results are significantly better than those obtained with LSTM.