Comparison of different Artificial Neural Networks for Bitcoin price forecasting

TL;DR

This paper compares how different sequence lengths in Artificial Neural Networks affect the accuracy of Bitcoin return predictions, highlighting the importance of sequence optimization for financial forecasting.

Contribution

It introduces a method to improve cryptocurrency return prediction accuracy by selecting optimal sequence lengths and excluding minor returns based on MAE thresholds.

Findings

Sequence length significantly impacts prediction accuracy.

Shorter sequences may lead to better forecasts for certain intervals.

Optimized sequence configurations enhance financial forecasting models.

Abstract

This study investigates the impact of varying sequence lengths on the accuracy of predicting cryptocurrency returns using Artificial Neural Networks (ANNs). Utilizing the Mean Absolute Error (MAE) as a threshold criterion, we aim to enhance prediction accuracy by excluding returns that are smaller than this threshold, thus mitigating errors associated with minor returns. The subsequent evaluation focuses on the accuracy of predicted returns that exceed this threshold. We compare four sequence lengths 168 hours (7 days), 72 hours (3 days), 24 hours, and 12 hours each with a return prediction interval of 2 hours. Our findings reveal the influence of sequence length on prediction accuracy and underscore the potential for optimized sequence configurations in financial forecasting models.