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

09/19/2023

∙

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.

READ FULL TEXT

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

How to effectively use machine learning models to predict the solutions for optimization problems: lessons from loss function

TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting

Predicting Coordinated Actuated Traffic Signal Change Times using LSTM Neural Networks

Components of Machine Learning: Binding Bits and FLOPS

Time Series Forecasting Models Copy the Past: How to Mitigate

Omnipredictors

Mean absolute deviations about the mean, the cut norm and taxicab correspondence analysis

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

Related Research

How to effectively use machine learning models to predict the solutions for optimization problems: lessons from loss function

TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecasting

Predicting Coordinated Actuated Traffic Signal Change Times using LSTM Neural Networks

Components of Machine Learning: Binding Bits and FLOPS

Time Series Forecasting Models Copy the Past: How to Mitigate

Omnipredictors

Mean absolute deviations about the mean, the cut norm and taxicab correspondence analysis