Journal ArticleDOI
Forecasting stock index returns using ARIMA-SVM, ARIMA-ANN, and ARIMA-random forest hybrid models
Manish Kumar,M. Thenmozhi +1 more
Reads0
Chats0
TLDR
The analysis shows that the hybrid ARIMA-SVM model is the best forecasting model to achieve high forecast accuracy and better returns.Abstract:
The purpose of this paper is to develop and identify the best hybrid model to predict stock index returns. We develop three different hybrid models combining linear ARIMA and non-linear models such as support vector machines (SVM), artificial neural network (ANN) and random forest (RF) models to predict the stock index returns. The performance of ARIMA-SVM, ARIMA-ANN and ARIMA-RF are compared with performance of ARIMA, SVM, ANN and RF models. The various competing models are evaluated in terms of statistical metrics and trading performance criteria via a trading strategy. The analysis shows that the hybrid ARIMA-SVM model is the best forecasting model to achieve high forecast accuracy and better returns.read more
Citations
More filters
Journal ArticleDOI
Literature review: Machine learning techniques applied to financial market prediction
TL;DR: Bibliographic survey techniques are applied to the literature about machine learning for predicting financial market values, resulting in a bibliographical review of the most important studies about this topic, and it was concluded that the research theme is still relevant and that the use of data from developing markets is a research opportunity.
Journal ArticleDOI
Hybrid structures in time series modeling and forecasting: A review
Zahra Hajirahimi,Mehdi Khashei +1 more
TL;DR: It can be observed that combined methods are viable and accurate approaches for time series forecasting and also the parallel–series hybrid structure can obtain more accurate and promising results than other those hybrid structures.
Journal ArticleDOI
Variable Selection in Time Series Forecasting Using Random Forests
TL;DR: The highest predictive performance of RF is observed when using a low number of recent lagged predictor variables, which could be useful in relevant future applications, with the prospect to achieve higher predictive accuracy.
Journal ArticleDOI
A deep learning framework for predicting cyber attacks rates
TL;DR: A deep learning framework by utilizing the bi-directional recurrent neural networks with long short-term memory, dubbed BRNN-LSTM is developed, which achieves a significantly higher prediction accuracy when compared with the statistical approach.
Journal ArticleDOI
Can artificial intelligence enhance the Bitcoin bonanza
Matheus José Silva de Souza,Fahad Almudhaf,Bruno Miranda Henrique,Ana Beatriz Silveira Negredo,Danilo Guimarães Franco Ramos,Vinicius Amorim Sobreiro,Herbert Kimura +6 more
TL;DR: Findings indicate that traders are able to earn conservative returns on the risk adjusted basis, even accounting for transaction costs, when using SVM, and suggests that ANN can explore short run informational inefficiencies to generate abnormal profits.
References
More filters
Journal ArticleDOI
Combining kohonen maps with arima time series models to forecast traffic flow
TL;DR: A hybrid method of short-term traffic forecasting is introduced; the KARIMA method, which uses a Kohonen self-organizing map as an initial classifier; each class has an individually tuned ARIMA model associated with it.
Proceedings Article
Machine Learning Benchmarks and Random Forest Regression
TL;DR: In this article, the authors revisited the formulation of random forests and investigated prediction performance on real-world and simulated datasets for which maximally sized trees do overfit, and revealed that gains can be realized by additional tuning to regulate tree size via limiting the number of splits and/or the size of nodes for which splitting is allowed.
Journal ArticleDOI
Neural Network Models for Time Series Forecasts
TL;DR: Across monthly and quarterly time series, the neural networks did significantly better than traditional methods in the present experiment, and were particularly effective for discontinuous time series.
Journal Article
Application of Support Vector Machines in Financial Time Series Forecasting
TL;DR: Analysis of the experiment results proves that it is advantageous to apply SVMs to forecast fmancial time series by comparing it with a back-propagation (BP)neural network.
Journal ArticleDOI
Forecasting Stock Indices: A Comparison of Classification and Level Estimation Models
TL;DR: Empirical experimentation suggests that the classification models outperform the level estimation models in terms of predicting the direction of the stock market movement and maximizing returns from investment trading.
Related Papers (5)
A hybrid ARIMA and support vector machines model in stock price forecasting
Ping-Feng Pai,Chih-Sheng Lin +1 more