Analysis and Forecasting of Financial Time Series Using CNN and LSTM-Based Deep Learning Models

2022 ◽  
pp. 405-423
Author(s):  
Sidra Mehtab ◽  
Jaydip Sen
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Financial Time Series ◽  
Learning Models ◽  
Financial Time

scholarly journals Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series

2020 ◽  
Vol 16 (10) ◽  
pp. 1401-1416
Author(s):  
Saugat Aryal ◽  
Dheynoshan Nadarajah ◽  
Prabath Lakmal Rupasinghe ◽  
Chandimal Jayawardena ◽  
Dharshana Kasthurirathna
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Financial Time Series ◽  
Learning Models ◽  
Financial Time

scholarly journals Deep Learning for Financial Time-Series Data Analytics: An Image Processing Based Approach

2020 ◽  
Vol 10 (1) ◽  
pp. 51-56
Author(s):  
Watthana Pongsena ◽  
Prakaidoy Ditsayabut ◽  
Nittaya Kerdprasop ◽  
Kittisak Kerdprasop
Keyword(s):  
Image Processing ◽  
Time Series ◽  
Deep Learning ◽  
Data Analytics ◽  
Time Series Data ◽  
Financial Time Series ◽  
Series Data ◽  
Financial Time

Prediction research of financial time series based on deep learning

2020 ◽  
Vol 24 (11) ◽  
pp. 8295-8312 ◽  
Author(s):  
Zhaoyi Xu ◽  
Jia Zhang ◽  
Junyao Wang ◽  
Zhiming Xu
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Financial Time Series ◽  
Financial Time

Financial Time Series Prediction Based on Deep Learning

2017 ◽  
Vol 102 (2) ◽  
pp. 683-700 ◽  
Author(s):  
Hongju Yan ◽  
Hongbing Ouyang
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Financial Time Series ◽  
Time Series Prediction ◽  
Financial Time

scholarly journals Online Learning with Radial Basis Function Networks

2021 ◽  
Author(s):  
Gabriel Borrageiro
Keyword(s):  
Time Series ◽  
Online Learning ◽  
Radial Basis Function ◽  
Basis Function ◽  
Financial Time Series ◽  
Gram Matrix ◽  
Radial Basis Function Networks ◽  
Learning Models ◽  
Financial Time ◽  
Radial Basis

We investigate the benefits of feature selection, nonlinear modelling and online learning when forecasting in financial time series. We consider the sequential and continual learning sub-genres of online learning. The experiments we conduct show that there is a benefit to online transfer learning, in the form of radial basis function networks, beyond the sequential updating of recursive least-squares models. We show that the radial basis function networks, which make use of clustering algorithms to construct a kernel Gram matrix, are more beneficial than treating each training vector as separate basis functions, as occurs with kernel Ridge regression. We demonstrate quantitative procedures to determine the very structure of the radial basis function networks. Finally, we conduct experiments on the log returns of financial time series and show that the online learning models, particularly the radial basis function networks, are able to outperform a random walk baseline, whereas the offline learning models struggle to do so.

scholarly journals Online Learning with Radial Basis Function Networks

2021 ◽  
Author(s):  
Gabriel Borrageiro
Keyword(s):  
Time Series ◽  
Online Learning ◽  
Radial Basis Function ◽  
Transfer Learning ◽  
Basis Function ◽  
Financial Time Series ◽  
Radial Basis Function Networks ◽  
Learning Models ◽  
Financial Time ◽  
Radial Basis

We investigate the benefits of feature selection, nonlinear modelling and online learning when forecasting financial time series. We combine sequential updating with continual learning, specifically transfer learning. We perform feature representation transfer through clustering algorithms that determine the analytical structure of radial basis function networks we construct. These networks achieve lower mean-square prediction errors than kernel ridge regression models, which arbitrarily use all training vectors as prototypes. We also demonstrate quantitative procedures to determine the very structure of the networks. Finally, we conduct experiments on the log-returns of financial time series and show that these online transfer learning models outperform a random-walk baseline. In contrast, the offline learning models struggle to do so.

Sign in / Sign up

Export Citation Format

Share Document