Please use this identifier to cite or link to this item:
https://rda.sliit.lk/handle/123456789/2570
Title: | Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series |
Authors: | Aryal, S Nadarajah, D Rupasinghe, P.L Jayawardena, C Kasthurirathna, D |
Keywords: | Financial Time Series Forecasting Multi-Step Prediction Deep Learning |
Issue Date: | 21-Oct-2020 |
Publisher: | researchgate.net |
Citation: | Aryal, Saugat & Nadarajah, Dheynoshan & Rupasinghe, Prabath & Jayawardena, Chandimal & Kasthurirathna, Dharshana. (2020). Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series. Journal of Computer Science. 16. 1401-1416. 10.3844/jcssp.2020.1401.1416. |
Series/Report no.: | Journal of Computer Science;16(10):1401-1416 |
Abstract: | Financial time series prediction has been a key topic of interest among researchers considering the complexity of the domain and also due to its significant impact on a wide range of applications. In contrast to one-step ahead prediction, multi-step forecasting is more desirable in the industry but the task is more challenging. In recent days, advancement in deep learning has shown impressive accomplishments across various tasks including sequence learning and time series forecasting. Although most previous studies are focused on applications of deep learning models for single-step ahead prediction, multi-step financial time series forecasting has not been explored exhaustively. This paper aims at extensively evaluating the performance of various state-of-the-art deep learning models for multiple multi-steps ahead prediction horizons on real-world stock and forex markets dataset. Specifically, we focus on Long-Short Term Memory (LSTM) network and its variations, Encoder-Decoder based sequence to sequence models, Temporal Convolution Network (TCN), hybrid Exponential SmoothingRecurrent Neural Networks (ES-RNN) and Neural Basis Expansion Analysis for interpretable Time Series forecasting (N-BEATS). Experimental results show that the latest deep learning models such as NBEATS, ES-LSTM and TCN produced better results for all stock market related datasets by obtaining around 50% less Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) scores for each prediction horizon as compared to other models. However, the conventional LSTM-based models still prove to be dominant in the forex domain by comparatively achieving around 2% less error values. |
URI: | http://rda.sliit.lk/handle/123456789/2570 |
ISSN: | 1549-3636 |
Appears in Collections: | Department of Computer Science and Software Engineering-Scopes |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
jcssp.2020.1401.1416-137.pdf | 1.03 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.