Stock Market Data Prediction Using Machine Learning Techniques

Torres, Pablo; Hernández-Álvarez, Myriam; Hernández, Edgar A. Torres; Yoo, Sang Guun

doi:10.1007/978-3-030-11890-7_52

Cited by 18 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, Reñosa et al (2020) used the deep learning-based LSTM approach on 1D time-series EEG data to classify EEG baselines which resulted in an accuracy of 89.23%. To classify emotions, 1D representation was used by Torres et al (2020) for hand-crafted features and trained them using the random forest model to achieve an accuracy of 71.22%. Yang et al (2020) utilized 1D representation of differential entropy with bidirectional LSTM (BiLSTM) to attain an accuracy of 84.21%.…”

Section: Introductionmentioning

confidence: 99%

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

Shah

Sinha

2022

Front. Signal Process.

View full text Add to dashboard Cite

Electroencephalographic (EEG) signals are electrical signals generated in the brain due to cognitive activities. They are non-invasive and are widely used to assess neurodegenerative conditions, mental load, and sleep patterns. In this work, we explore the utility of representing the inherently single dimensional time-series in different dimensions such as 1D-feature vector, 2D-feature maps, and 3D-videos. The proposed methodology is applied to four diverse datasets: 1) EEG baseline, 2) mental arithmetic, 3) Parkinson’s disease, and 4) emotion dataset. For a 1D analysis, popular 1D features hand-crafted from the time-series are utilized for classification. This performance is compared against the data-driven approach of using raw time-series as the input to the deep learning framework. To assess the efficacy of 2D representation, 2D feature maps that utilize a combination of the Feature Pyramid Network (FPN) and Atrous Spatial Pyramid Pooling (ASPP) is proposed. This is compared against an approach utilizing a composite feature set consisting of 2D feature maps and 1D features. However, these approaches do not exploit spatial, spectral, and temporal characteristics simultaneously. To address this, 3D EEG videos are created by stacking spectral feature maps obtained from each sub-band per time frame in a temporal domain. The EEG videos are the input to a combination of the Convolution Neural Network (CNN) and Long–Short Term Memory (LSTM) for classification. Performances obtained using the proposed methodologies have surpassed the state-of-the-art for three of the classification scenarios considered in this work, namely, EEG baselines, mental arithmetic, and Parkinson’s disease. The video analysis resulted in 92.5% and 98.81% peak mean accuracies for the EEG baseline and EEG mental arithmetic, respectively. On the other hand, for distinguishing Parkinson’s disease from controls, a peak mean accuracy of 88.51% is achieved using traditional methods on 1D feature vectors. This illustrates that 3D and 2D feature representations are effective for those EEG data where topographical changes in brain activation regions are observed. However, in scenarios where topographical changes are not consistent across subjects of the same class, these methodologies fail. On the other hand, the 1D analysis proves to be significantly effective in the case involving changes in the overall activation of the brain due to varying degrees of deterioration.

show abstract

Section: Introductionmentioning

confidence: 99%

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

Shah

Sinha

2022

Front. Signal Process.

View full text Add to dashboard Cite

show abstract

“…ey validated their proposed model on eight different large stock datasets in various domains and attained better performance than existing methods. Similarly, Torres et al proposed an algorithm based on random trees and the multilayer perceptron (MLP) methods to analyze Apple's stock data [27].…”

Section: Stock Market Analysis Using Traditional Methodsmentioning

confidence: 99%

An Empirical Study of Macroeconomic Factors and Stock Returns in the Context of Economic Uncertainty News Sentiment Using Machine Learning

et al. 2022

View full text Add to dashboard Cite

Stock markets accurately reflect countries’ economic health, and stock returns are tightly related to economic indices. One popular area of financial research is the factors that influence stock returns. Several investigations have frequently cited macroeconomic factors, among numerous elements. Therefore, this study focuses on the empirical analysis of the relationship between macroeconomic factors and stock market returns. When a stock market becomes increasingly volatile, it becomes susceptible to economic uncertainty news, and information on social media platforms. Thus, we incorporated a new dimension of economic uncertainty news sentiment (EUNS) for stock return predictions. We employed the daily data ofgold index, crude oil price, interest rate, exchange rate, and stock returns for a set of countries from January 2010 to December 2020. Subsequently, to compute coefficients, we conducted a regression analysis using one of the more sophisticated approaches: single-layer neural networks and ordinary least square regression. In addition, we only computed EUNS for the period of the fiscal budget announcement for the US, Turkey, and Hong Kong. The results indicate that the gold index, interest rate, and exchange rate are highly significant and negative macroeconomic factors for all analyzed countries. These findings also indicate that EUNS is important and detrimental for projecting stock returns.

show abstract

“…Similar conclusions regarding the benefits of using machine learning have also been recognised by researchers who have focused on only one company in a portfolio. In particular, their study focused on the usefulness of supervised machine learning algorithms (Torres et al, 2019). In the 2020 study, on the other hand, the researchers focused on analysing three companies from the binding sectors of finance, IT and health sciences listed on the National Stock Exchange.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting Prices of Shares Listed on the Warsaw Stock Exchange Using Machine Learning

Jóźwicki

2022

Journal of Intercultural Management

View full text Add to dashboard Cite

Objective: The technology developing before our eyes is entering many areas of life and has an increasing influence on shaping human behavior. Undoubtedly, it can be stated that one such area is trading on stock exchanges and other markets that offer investors the opportunity to allocate their capital. Thanks to widespread access to the Internet and the computing capabilities of computers used in the daily activities of investors, the nature of their working has changed significantly, compared to what we observed even 10–15 years ago. At present, stock exchange orders may be placed in person using various types of brokerage investment accounts, which allow the investor to view real-time quotations which opens up a whole new range of opportunities for investorsIts skillful application during the stock market game can positively influence a player’s investment performance.Machine learning is a branch of artificial intelligence and computer science that focuses on using data and algorithms to solve decision-making problems based on large amounts of information. In machine learning, algorithms find patterns and relationships in large data sets and make the best decisions and predictions based on this analysis. Methodology: The main objective of this paper is to investigate and evaluate the applicability of machine learning for investment decisions in equity markets. The analysis undertaken focuses on so-called day-trading, i.e. investing for very short periods of time, often involving only a single trading session. The hypothesis adopted is that the use of machine learning can contribute to a positive return for a stock market player making short-term investments. Findings: This paper uses the Azure Microsoft Machine Learning Studio tool to enable machine learning-based calculations. It is a widely available cloud computing platform that provides an investor interested in creating a model and testing it. The calculations were made according to two schemes. The first involves teaching the model by taking 50% of the companies randomly selected from all companies, while the second involves teaching the model by taking 80% of the companies randomly selected from all companies. Value Added: The results from the study indicate that investors can use machine learning to earn returns that are attractive to them. Depending on the teaching model (50% or 80% companies), daily returns can range from 1.07% to even 4.23%. Recommendations: The results obtained offer investors the prospect of using the method presented in the article in their capital management strategies, which of course requires them to adapt the techniques used so far to the specifics of machine learning. However, it is necessary to note that the presented method requires that each time the data on which the forecast was made be updated..Further research is needed to determine the impact of the number of companies on the effectiveness of the learning process.

show abstract

Stock Market Data Prediction Using Machine Learning Techniques

Cited by 18 publications

References 8 publications

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

An investigation of the multi-dimensional (1D vs. 2D vs. 3D) analyses of EEG signals using traditional methods and deep learning-based methods

An Empirical Study of Macroeconomic Factors and Stock Returns in the Context of Economic Uncertainty News Sentiment Using Machine Learning

Forecasting Prices of Shares Listed on the Warsaw Stock Exchange Using Machine Learning

Contact Info

Product

Resources

About