Forecasting stock price movement direction by machine learning algorithm

Khoa, Bùi Thành; Huynh, Tran Trong

doi:10.11591/ijece.v12i6.pp6625-6634

Cited by 14 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last metric used is the 𝐹1-score to measure the performance model on predicting price movement direction. The actual 𝑑 𝑖 and predicted 𝑑 ̂𝑖 direction calculation shown in (13) and (14). The up direction is represented by 1, and the down direction is represented by 0.…”

Section: Evaluationsmentioning

confidence: 99%

Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study

Haryono,

Sarno,

Sungkono

2024

IJECE

View full text Add to dashboard Cite

In 2022, the Indonesia stock exchange (IDX) listed 825 companies, making it challenging to identify low-risk companies. Stock price forecasting and price movement prediction are vital issues in financial works. Deep learning has previously been implemented for stock market analysis, with promising results. Because of the differences in architecture and stock issuers in each study report, a consensus on the best stock price forecasting model has yet to be reached. We present a methodology for comparing the performance of convolutional neural networks (CNN), gated recurrent units (GRU), long short-term memory (LSTM), and graph convolutional networks (GCN) layers. The four layers types combination yields 11 architectures with two layers stacked maximum, and the architectures are performance compared in stock price predicting. The dataset consists of open, highest, lowest, closed price, and volume transactions and has 2,588,451 rows from 727 companies in IDX. The best performance architecture was chosen by a vote based on the coefficient of determination (R2), mean squared error (MSE), root mean square error (RMSE), mean absolute percent error (MAPE), and f1-score. TFGRU is the best architecture, producing the finest results on 315 companies with an average score of RMSE is 553.327, MAPE is 0.858, and f1-score is 0.456.

show abstract

Section: Evaluationsmentioning

confidence: 99%

Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study

Haryono,

Sarno,

Sungkono

2024

IJECE

View full text Add to dashboard Cite

show abstract

“…Thus, ML approaches can be used to build highperformance SPF systems without expert knowledge. The traditional ML algorithms, such as ANNs, 11,30,31 k-nearest neighbors (KNN), 32,33 support vector machine (SVM), [34][35][36][37][38][39][40] ensemble models, [41][42][43][44][45][46][47] and BN, 48,49 have been successfully and widely used in SPF systems. Table 2 presents articles on SPF based on ML approaches.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

A bibliometric literature review of stock price forecasting: From statistical model to deep learning approach

Vuong,

Phu,

Van Nguyen

et al. 2024

Science Progress

View full text Add to dashboard Cite

We introduce a comprehensive analysis of several approaches used in stock price forecasting, including statistical, machine learning, and deep learning models. The advantages and limitations of these models are discussed to provide an insight into stock price forecasting. Traditional statistical methods, such as the autoregressive integrated moving average and its variants, are recognized for their efficiency, but they also have some limitations in addressing non-linear problems and providing long-term forecasts. Machine learning approaches, including algorithms such as artificial neural networks and random forests, are praised for their ability to grasp non-linear information without depending on stochastic data or economic theory. Moreover, deep learning approaches, such as convolutional neural networks and recurrent neural networks, can deal with complex patterns in stock prices. Additionally, this study further investigates hybrid models, combining various approaches to explore their strengths and counterbalance individual weaknesses, thereby enhancing predictive accuracy. By presenting a detailed review of various studies and methods, this study illuminates the direction of stock price forecasting and highlights potential approaches for further studies refining the stock price forecasting models.

show abstract

“…Bui [18] used the rolling window method to forecast the Stock Price Movement Direction (SPMD) of 30 stocks in the VN30 basket, comparing Support Vector Machines (SVM), logistic regression, and Artificial Neural Networks (ANN). Pham et al [19] explored the chances that some stock components in the VN30 basket could outperform the index by simultaneously applying Long Short-Term Memory (LSTM) and Ichimoku Cloud trading strategy, selecting three stocks with the best profit potential to sell 10 days later.…”

Section: Theoretical Background For Stock-market Trends Predictionmentioning

confidence: 99%

“…However, the study had some limitations, such as the low accuracy of certain predictors, high standard deviation, and the omission of some essential tests that ensure a model is BLUE (Best, Linear, Unbiased Estimator). Bui [18] applied a rolling window method to forecast the Stock Price Movement Direction (SPMD) of the 30 stocks in the VN30 basket. They compared three…”

Section: Review Of Previous Research On the Vn30 Indexmentioning

confidence: 99%

Forecasting the VN30 Index: Insights into Vietnam’s Stock Market Trends

Paientko

2024

SIAM

View full text Add to dashboard Cite

This research paper examines the potential of forecasting the VN30 index, a prominent benchmark in the Vietnamese stock market, using the Auto Regressive Integrated Moving Average (ARIMA) model. Given the rapid evolution of the Vietnamese stock market since its inception in 2000, it presents unique challenges and opportunities for investors and policymakers. The increasing trading activity and the market's relatively low efficiency make accurate forecasting essential for informed decision-making. The purpose of this study is to determine if the ARIMA model can effectively predict the future values of the VN30 index, providing insights into market trends and assisting stakeholders in navigating the complexities of the Vietnamese stock market. The methodology employed involves a comprehensive approach based on the theory of change and the steps outlined by Hyndman [1], including data visualization, variance stabilization, model selection, and residual analysis. Data used for this study consist of monthly and daily observations of the VN30 index over various periods, allowing for a robust analysis of market behavior. Findings indicate that the ARIMA model can be a valuable tool for forecasting in emerging markets like Vietnam, although challenges related to information transparency and corporate disclosure persist. The results suggest that the VN30 index's future values generally align with ARIMA's prediction interval, offering a degree of confidence for investors and market analysts. However, the study also highlights the need for ongoing improvements in market efficiency and transparency to enhance forecasting accuracy. This paper contributes to the existing literature by demonstrating the applicability of ARIMA in a developing market context and providing practical guidance for investors and policymakers.

show abstract

Forecasting stock price movement direction by machine learning algorithm

Cited by 14 publications

References 28 publications

Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study

Stock price forecasting in Indonesia stock exchange using deep learning: a comparative study

A bibliometric literature review of stock price forecasting: From statistical model to deep learning approach

Forecasting the VN30 Index: Insights into Vietnam’s Stock Market Trends

Contact Info

Product

Resources

About