Mean Absolute Directional Loss as a New Loss Function for Machine Learning Problems in Algorithmic Investment Strategies
This addresses the need for better loss functions in algorithmic investment strategies, offering a domain-specific improvement for financial forecasting.
The paper tackles the problem of inadequate loss functions for optimizing machine learning models in financial time series forecasting for algorithmic investment strategies by proposing the Mean Absolute Directional Loss (MADL) function. It shows that MADL improves hyperparameter selection for LSTM models, leading to more efficient strategies with better risk-adjusted returns on out-of-sample data for Bitcoin and Crude Oil.
This paper investigates the issue of an adequate loss function in the optimization of machine learning models used in the forecasting of financial time series for the purpose of algorithmic investment strategies (AIS) construction. We propose the Mean Absolute Directional Loss (MADL) function, solving important problems of classical forecast error functions in extracting information from forecasts to create efficient buy/sell signals in algorithmic investment strategies. Finally, based on the data from two different asset classes (cryptocurrencies: Bitcoin and commodities: Crude Oil), we show that the new loss function enables us to select better hyperparameters for the LSTM model and obtain more efficient investment strategies, with regard to risk-adjusted return metrics on the out-of-sample data.