Mean Absolute Directional Loss as a New Loss Function for Machine Learning Problems in Algorithmic Investment Strategies

TL;DR

This paper introduces the Mean Absolute Directional Loss (MADL), a new loss function for machine learning models in financial forecasting, improving hyperparameter selection and investment strategy performance.

Contribution

The paper proposes MADL, a novel loss function tailored for financial time series forecasting, addressing limitations of traditional error functions in investment strategy development.

Findings

MADL improves hyperparameter tuning for LSTM models.

Strategies optimized with MADL show better risk-adjusted returns.

Empirical results on Bitcoin and Crude Oil data validate MADL's effectiveness.

Abstract

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.