Genetic Algorithm for the Mutual Information-Based Feature Selection in Univariate Time Series Data

Siddiqi, Umair F.; Sait, Sadiq M.; Kaynak, Okyay

doi:10.1109/access.2020.2964803

Cited by 15 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, feature selection techniques reduce factors containing redundant information, while efficiency, accuracy and interpretability of the prediction model. In other words, an efficient feature selection procedure reduces the training time of the model by pulling out of the input dataset redundant factors, while avoiding overfitting of the financial data [ 28 , 36 ]. Nonetheless the several advantages of feature selection procedures, few studies have applied them in combination with predictive models for stock index trends.…”

Section: Literature Reviewmentioning

confidence: 99%

Stock index trend prediction based on TabNet feature selection and long short-term memory

2022

View full text Add to dashboard Cite

In this study, we propose a predictive model TabLSTM that combines machine learning methods such as TabNet and Long Short-Term Memory Neural Network (LSTM) with a complete factor library for stock index trend prediction. Our motivation is based on the notion that there are numerous interrelated factors in the stock market, and the factors that affect each stock are different. Therefore, a complete factor library and an efficient feature selection technique are necessary to predict stock index. In this paper, we first build a factor database that includes macro, micro and technical indicators. Successively, we calculate the factor importance through TabNet and rank them. Based on a prespecified threshold, the optimal factors set will include only the highest-ranked factors. Finally, using the optimal factors set as input information, LSTM is employed to predict the future trend of 4 stock indices. Empirical validation of the model shows that the combination of TabNet for factors selection and LSTM outperforms existing methods. Moreover, constructing a factor database is necessary for stock index prediction. The application of our method does not only show the feasibility to predict stock indices across different financial markets, yet it also provides an complete factor database and a comprehensive architecture for stock index trend prediction, which may provide some references for stock forecasting and quantitative investments.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Stock index trend prediction based on TabNet feature selection and long short-term memory

2022

View full text Add to dashboard Cite

show abstract

“…Results Limitations [12] Fuzzy C-Means Accuracy = 96.3% Increased computational time. [13] Genetic Algorithm Maximal relevance is approx. 5.…”

Section: Ref Technique Usedmentioning

confidence: 99%

Multi Objective Optimization Based Feature Selection Algorithms for Big Data Analytics: A Review

Shukla¹,

Tiwari²

2021

IJAINN

View full text Add to dashboard Cite

Dimension reduction or feature selection is thought to be the backbone of big data applications in order to improve performance. Many scholars have shifted their attention in recent years to data science and analysis for real-time applications using big data integration. It takes a long time for humans to interact with big data. As a result, while handling high workload in a distributed system, it is necessary to make feature selection elastic and scalable. In this study, a survey of alternative optimizing techniques for feature selection are presented, as well as an analytical result analysis of their limits. This study contributes to the development of a method for improving the efficiency of feature selection in big complicated data sets.

show abstract

“…Siddiqi et al [12] suggested the architecture of the genetic algorithm (GA) wherein the fitness of solutions is made of two components. A feature-selection measure will be the first, like MI, JMI, or mRMR.…”

Section: Related Workmentioning

confidence: 99%

An Analytical Review on Feature Reduction for Big Data Analytics using Machine Learning

Kulhare¹,

Veenadhari²,

Sharma³

2021

New Frontiers in Communication and Intelligent Systems

View full text Add to dashboard Cite

There is an explosive growth of data due to advancements in computer methods. With ML techniques, working on a really massive quantity of data is a big problem. As a result, handling and computing on a very vast, varied, and diverse dataset seems a difficult undertaking. The purpose of this study is to provide a quick overview of several dimensionality reduction/feature selection techniques. A summary of the contributions of scholars to the development of feature selection methods for huge datasets is provided. This study is driven to create a hybrid, resilient, adjustable, as well as dynamical feature selection approach to classify huge datasets by examining current challenges.

show abstract

Genetic Algorithm for the Mutual Information-Based Feature Selection in Univariate Time Series Data

Cited by 15 publications

References 29 publications

Stock index trend prediction based on TabNet feature selection and long short-term memory

Stock index trend prediction based on TabNet feature selection and long short-term memory

Multi Objective Optimization Based Feature Selection Algorithms for Big Data Analytics: A Review

An Analytical Review on Feature Reduction for Big Data Analytics using Machine Learning

Contact Info

Product

Resources

About