Alternative Loss Function in Evaluation of Transformer Models
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.
Similar Papers
Generalized Mean Absolute Directional Loss as a Solution to Overfitting and High Transaction Costs in Machine Learning Models Used in High-Frequency Algorithmic Investment Strategies
Computational Finance
Helps trading computers make smarter, cheaper money.
On Evaluating Loss Functions for Stock Ranking: An Empirical Analysis With Transformer Model
Machine Learning (CS)
Helps computers pick winning stocks better.
Adaptive Online Learning with LSTM Networks for Energy Price Prediction
Machine Learning (CS)
Predicts electricity prices better for the power grid.