Alternative Loss Function in Evaluation of Transformer Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Michańków, Jakub, Sakowski, Paweł, Ślepaczuk, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915407340765184
author Michańków, Jakub
Sakowski, Paweł
Ślepaczuk, Robert
author_facet Michańków, Jakub
Sakowski, Paweł
Ślepaczuk, Robert
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16548
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Alternative Loss Function in Evaluation of Transformer Models
Michańków, Jakub
Sakowski, Paweł
Ślepaczuk, Robert
Computational Finance
Machine Learning
Trading and Market Microstructure
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.
title Alternative Loss Function in Evaluation of Transformer Models
topic Computational Finance
Machine Learning
Trading and Market Microstructure
url https://arxiv.org/abs/2507.16548