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

Vedant Shah, Gautam Shroff

Keywords: time-series, forecasting, financial-analysis, data-augmentation, meta-learning, synthetic-data

TL;DR: We use advanced deep learning techniques - meta learning and augmentation with synthetic data in an attempt to improve market data forecasting using various deep learning models but ARIMA still outperforms.

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.

Category: Negative result: I would like to share my insights and negative results on this topic with the community