Alternative Loss Function in Evaluation of Transformer Models
This addresses loss function selection for algorithmic trading models, though it appears incremental as it applies an existing loss function to standard architectures.
The researchers tackled the problem of selecting appropriate loss functions for machine learning models in quantitative finance by applying the Mean Absolute Directional Loss (MADL) function to Transformer and LSTM models on equity and cryptocurrency data. They found that Transformers significantly outperformed LSTMs in almost every case.
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.