Computational Intelligence Techniques Used for Stock Market Prediction: A Systematic Review

Pauli, Suellen Teixeira Zavadzki de; Kleina, Mariana; Drozda, Fabiano Oscar; Marques, Marcos Augusto Mendes

doi:10.1109/tla.2020.9082218

Cited by 15 publications

(3 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The performance of the proposed framework is evaluated on public datasets for comparison with the existing methods. 1) Human Activity Classification (HAC) database [23]: An experiment is done to collect a real-time human activity dataset. 2) Daily and Sports activity (DSA): MTS data on 19 different types of human activities with ground truth class labels are included in the DSA [24] database.…”

Section: H Performance Evaluation On Existing Datsetsmentioning

confidence: 99%

Early MTS Forecasting for Dynamic Stock Prediction: A Double Q-Learning Ensemble Approach

Kumar,

Alsamhi,

Kumar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Multivariate time series (MTS) forecasting is a rapidly expanding field with diverse and futuristic applications. However, traditional statistical learning models need more prediction accuracy when faced with dynamic variability, non-linearity, and non-stationarity, as well as the challenge of selecting MTS data for classification. Moreover, the existing methods for early classification of multivariate time series data suffer from numerous severe challenges, including evaluating the length of testing the MTS data component, which must be equal to the training MTS data component, and the availability of faulty data components in MTS. To address this issue, we propose a novel framework for early MTS forecasting using double Q-learning-based ensemble techniques to improve prediction accuracy. Our framework uses Q-learning agents to select optimal actions, which results in maximum rewards and accurate prediction. We investigate the ensemble behavior of learned agents using double Q-learning and Gaussian Process Classifiers (GPC) for early forecasting of MTS data. We also determine the minimum required time-series length for classifying faulty data components using the probabilistic Auto-Regressive Integrated Moving Average (ARIMA) model, enhancing framework robustness and mitigating miss-classification accuracy. Our proposed framework achieves 99.89% accuracy for early forecasting, surpassing existing methods based on different benchmark settings and publicly available multivariate time-series datasets. The framework provides a promising solution to the challenges of accurate MTS forecasting and offers insights into the early prediction of recent stock market trading data.

show abstract

Section: H Performance Evaluation On Existing Datsetsmentioning

confidence: 99%

Early MTS Forecasting for Dynamic Stock Prediction: A Double Q-Learning Ensemble Approach

Kumar,

Alsamhi,

Kumar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Studies from conference proceedings are not excluded from this SLR, as most studies are generally published in conference proceedings. Due to the increased workload significantly when reviewing studies some of the SLR papers did not use the conference proceedings as in [24]. In contrast to [18], [19] included conference proceedings as the main study in their systematic literature review.…”

Section: Threats To Validitymentioning

confidence: 99%

The Stock Exchange Prediction using Machine Learning Techniques: A Comprehensive and Systematic Literature Review

Wiranata

Djunaidy

2021

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

This literature review identifies and analyzes research topic trends, types of data sets, learning algorithm, methods improvements, and frameworks used in stock exchange prediction. A total of 81 studies were investigated, which were published regarding stock predictions in the period January 2015 to June 2020 which took into account the inclusion and exclusion criteria. The literature review methodology is carried out in three major phases: review planning, implementation, and report preparation, in nine steps from defining systematic review requirements to presentation of results. Estimation or regression, clustering, association, classification, and preprocessing analysis of data sets are the five main focuses revealed in the main study of stock prediction research. The classification method gets a share of 35.80% from related studies, the estimation method is 56.79%, data analytics is 4.94%, the rest is clustering and association is 1.23%. Furthermore, the use of the technical indicator data set is 74.07%, the rest are combinations of datasets. To develop a stock prediction model 48 different methods have been applied, 9 of the most widely applied methods were identified. The best method in terms of accuracy and also small error rate such as SVM, DNN, CNN, RNN, LSTM, bagging ensembles such as RF, boosting ensembles such as XGBoost, ensemble majority vote and the meta-learner approach is ensemble Stacking. Several techniques are proposed to improve prediction accuracy by combining several methods, using boosting algorithms, adding feature selection and using parameter and hyper-parameter optimization.

show abstract

“…iv Implementar a integração do sistema proposto com outras técnicas de inteligência artificial, como a lógica fuzzy, de tal maneira a capturar nuâncias dos dados, aumentando as informações disponíveis para a Rede Neural, tal qual diversas abordagens tem sido utilizadas nos mercados de ações (ZAVADZKI et al, 2020).…”

Section: Propostas De Desenvolvimentos Futurosunclassified

Estratégias de predição de preços do mercado livre de energia por redes neurais artificiais e filtragem estocástica

Nascimento¹

View full text Add to dashboard Cite

O Preço de Liquidação das Diferenças (PLD) é utilizado como base na comercialização de energia elétrica no mercado de curto prazo. O conhecimento dos seus valores futuros e tendências reduz a insegurança na tomada de decisões, permitindo que os agentes de mercado decidam as estratégias mais adequadas e estabeleçam contratações bem-sucedidas, maximizando os lucros e minimizando os riscos de seus empreendimentos. O PLD é, no entanto, influenciado por diversos fatores ligados principalmente às incertezas das demandas e à hidrologia bem como fatores sociais e políticos, o que lhe confere alta volatilidade, sazonalidade, saturação de valores e comportamento estocástico. Desta forma, o presente trabalho propõe uma abordagem investigativa para a predição das tendências futuras do PLD por meio de Redes Neurais Artificiais e Filtragem Estocástica, com a motivação de auxiliar o processo de decisão da compra de energia no mercado de curto prazo. Tal abordagem consiste na combinação de uma rede neural do tipo recorrente com um filtro na saída para atenuar os ruídos inerentes aos dados auxiliando na preservação das tendências dos dados futuros. A rede foi treinada por meio do algoritmo ADAM e é aplicada ao mercado brasileiro de energia. A escolha dos dados de entrada da rede foi feita a partir de análises estatísticas de correlação cruzada entre as séries temporais das variáveis de interesse. Os resultados mostram uma boa capacidade de predição com um bom acompanhamento das tendências da variável de interesse ao longo do ano, oferecendo seus principais comportamentos e tendências aos operadores de mercado, auxiliando-os nas tomadas de decisões de compra e venda de energia.

show abstract

Computational Intelligence Techniques Used for Stock Market Prediction: A Systematic Review

Cited by 15 publications

References 89 publications

Early MTS Forecasting for Dynamic Stock Prediction: A Double Q-Learning Ensemble Approach

Early MTS Forecasting for Dynamic Stock Prediction: A Double Q-Learning Ensemble Approach

The Stock Exchange Prediction using Machine Learning Techniques: A Comprehensive and Systematic Literature Review

Estratégias de predição de preços do mercado livre de energia por redes neurais artificiais e filtragem estocástica

Contact Info

Product

Resources

About