Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!

TL;DR

This study compares deep-learning models and traditional ARIMA for financial time-series forecasting, finding ARIMA still outperforms advanced deep-learning techniques despite data augmentation and meta-learning efforts.

Contribution

It provides a comprehensive benchmark of deep-learning models against ARIMA in financial forecasting, including synthetic data generation and meta-learning applications.

Findings

ARIMA outperforms deep-learning models in accuracy

Synthetic data and meta-learning do not significantly improve deep-learning performance

Traditional models remain competitive despite advanced techniques

Abstract

Deep-learning techniques have been successfully used for time-series forecasting and have often shown superior performance on many standard benchmark datasets as compared to traditional techniques. Here we present a comprehensive and comparative study of performance of deep-learning techniques for forecasting prices in financial markets. We benchmark state-of-the-art deep-learning baselines, such as NBeats, etc., on data from currency as well as stock markets. We also generate synthetic data using a fuzzy-logic based model of demand driven by technical rules such as moving averages, which are often used by traders. We benchmark the baseline techniques on this synthetic data as well as use it for data augmentation. We also apply gradient-based meta-learning to account for non-stationarity of financial time-series. Our extensive experiments notwithstanding, the surprising result is that the standard ARIMA models outperforms deep-learning even using data augmentation or meta-learning. We conclude by speculating as to why this might be the case.