Score: 0

Alternative Loss Function in Evaluation of Transformer Models

Published: July 22, 2025 | arXiv ID: 2507.16548v2

By: Jakub Michańków, Paweł Sakowski, Robert Ślepaczuk

Potential Business Impact:

Makes trading computers predict prices better.

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.

Country of Origin
🇵🇱 Poland

Page Count
12 pages

Category
Quantitative Finance:
Computational Finance