Stock Market Movement Prediction using Disparate Text Features with Machine Learning

Bouktif, Salah; Fiaz, Ali; Awad, Mamoun

doi:10.1109/icds47004.2019.8942303

Cited by 7 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bouktif ve ark. çalışmasında AMZN NASDAQ üzerinde hisse senedi artma azalma yönü tahmin edilmiştir [11]. Yapılan çalışmada DVM, lojistik regresyon (LR), ileri beslemeli sinir ağları (Feed Forward Neural Networks), RO ve ekstrem gradyan artırma (Extreme Gradient Boosting) modelleri kullanılmıştır.…”

Section: Li̇teratür Taramasi (Literature Review)unclassified

“…Özniteliklerin de oluşturulmasıyla beraber modelimizde RO sınıflandırma algoritması kullanılmıştır. Sınıflandırma algoritması olarak RO'nun seçilme sebebi, pek çok çalışma tarafından bu alanda iyi başarım sonuçları elde ettiğinin belirtilmesidir [11], [16], [17], [19]. RO algoritması, eğitim aşamasında çok sayıda karar ağacının oluşturulmasıyla çalışan bir topluluk öğrenmesi yöntemidir.…”

Section: Model Parametreleri̇ Ve Deneysel Sonuçlar (Model Parameters ...unclassified

“…Paralel bir şekilde, bu çalışma sonucunda da kullanılan teknik indikatörlerin yüksek başarım değerleri elde ettiği görülmüştür. Ayrıca literatürdeki pek çok çalışma, finansal makalelerden [13], [15], borsa ve finans ile ilgili haber metinlerinden [10], [12] ve popüler sosyal medya platformlarında paylaşılan kısa iletilerden elde edilen duygu skor değerlerinin [11], [14] borsa endekslerinin trend analizlerinde kullanılabileceğini belirtmiştir. Bu çalışmada da bazı periyotlar için haber metinlerinden ele edilen duygu değerlerinin BİST100 endeksi üzerinde etkili olduğu gözlemlenmiştir.…”

Section: F-skor Bti̇ök + S3unclassified

“…Ateş ve Güran çalışmaları ile [9], sosyal medyada paylaşılan kısa iletiler ile BİST30 endeksi arasında anlamlı korelasyon ilişkileri olduğunu belirtmiş ve ülkemiz adına önemli olayların olduğu bir dönemde duygu değerleri ve endeks arasında Granger nedensellik ilişkine rastlandığını ifade etmişlerdir. Pek çok çalışmanın deneysel olarak elde etmiş olduğu bulgular neticesinde günümüzde haber kaynaklarının beklenmedik olaylar ile ilgili yansıttığı olumlu ve/veya olumsuz algıların finansal piyasaları etkileyebildiği görülmektedir [10][11][12][13][14][15]. Bu çalışmalarda, olumlu ve olumsuz haber sayılarının kullanılması ile elde edilen duygu değerlerinin, gerek borsa endekslerinin gelecekteki değerlerinin ön görülmesinde; gerekse endekslerin pozitif/negatif yönlü hareketlerinin tahmin edilmesinde etkili olduğu belirtilmiştir.…”

Section: Gi̇ri̇ş (Introduction)unclassified

See 3 more Smart Citations

Predicting BIST 100 Index Movement by using Sentiment Scores and Technical Indicators during the COVID-19 Pandemic

ALACA

Güran

2022

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

Sentiment analysis includes the stages of identifying the positive, negative or neutral emotions contained in the text data. Positive and/or negative emotions reflected by the text data can affect the decision-making processes of people, small or large-scale companies. Emotions reflected by documents can be vectorized with sentiment scores and these scores could be useful to forecast time series models. As it is known, the coronavirus, which emerged in Wuhan, China on December 1, 2019 caused a global pandemic all around the world. The Covid-19 pandemic has brought sharp and sudden declines in global and domestic stock markets. Within the scope of our study, it was analyzed whether the sentiment scores obtained from the Covid-19 related news documents were effective in forcasting the trend of the Bist100 index. Technical indicators that have great importance in estimating stock market indices, were also used in the analysis. Hence, the effect of sentiment scores and technical indicators in determining the trend of the stock market index during the pandemic could be observed. As a result of the study, it was observed that the sentiment scores were effective to predict the price trend of stock market index for some periods.

show abstract

Section: Li̇teratür Taramasi (Literature Review)unclassified

Section: Model Parametreleri̇ Ve Deneysel Sonuçlar (Model Parameters ...unclassified

Section: F-skor Bti̇ök + S3unclassified

Section: Gi̇ri̇ş (Introduction)unclassified

See 2 more Smart Citations

Predicting BIST 100 Index Movement by using Sentiment Scores and Technical Indicators during the COVID-19 Pandemic

ALACA

Güran

2022

Bilişim Teknolojileri Dergisi

View full text Add to dashboard Cite

show abstract

“…ML techniques can be categorized into shallow and deep learning methods. Shallow models, such as naive Bayes [20], logistic regression [21], support vector machines [22,23], decision trees [2,24], random forests [25], and early neural networks such as multilayer perceptron [26][27][28], have been extensively examined in this domain. However, following the emergence of deep learning methods, stock market prediction, as with many other data analysis tasks, has been dominated by deep neural networks [29].…”

Section: Introductionmentioning

confidence: 99%

User2Vec: A Novel Representation for the Information of the Social Networks for Stock Market Prediction Using Convolutional and Recurrent Neural Networks

2023

View full text Add to dashboard Cite

Predicting stock market trends is an intriguing and complex problem, which has drawn considerable attention from the research community. In recent years, researchers have employed machine learning techniques to develop prediction models by using numerical market data and textual messages on social networks as their primary sources of information. In this article, we propose User2Vec, a novel approach to improve stock market prediction accuracy, which contributes to more informed investment decision making. User2Vec is a unique method that recognizes the unequal impact of different user opinions on specific stocks, and it assigns weights to these opinions based on the accuracy of their associated social metrics. The User2Vec model begins by encoding each message as a vector. These vectors are then fed into a convolutional neural network (CNN) to generate an aggregated feature vector. Following this, a stacked bi-directional long short-term memory (LSTM) model provides the final representation of the input data over a period. LSTM-based models have shown promising results by effectively capturing the temporal patterns in time series market data. Finally, the output is fed into a classifier that predicts the trend of the target stock price for the next day. In contrast to previous attempts, User2Vec considers not only the sentiment of the messages, but also the social information associated with the users and the text content of the messages. It has been empirically proven that this inclusion provides valuable information for predicting stock direction, thereby significantly enhancing prediction accuracy. The proposed model was rigorously evaluated using various combinations of market data, encoded messages, and social features. The empirical studies conducted on the Dow Jones 30 stock market showed the model’s superiority over existing state-of-the-art models. The findings of these experiments reveal that including social information about users and their tweets, in addition to the sentiment and textual content of their messages, significantly improves the accuracy of stock market prediction.

show abstract

Prediction of Closing Stock Prices Using the Artificial Neural Network in the Market for Alternative Investment (MAI) of the Stock Exchange of Thailand (SET)

Chaysiri

Ngauv

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Stock Market Movement Prediction using Disparate Text Features with Machine Learning

Cited by 7 publications

References 16 publications

Predicting BIST 100 Index Movement by using Sentiment Scores and Technical Indicators during the COVID-19 Pandemic

Predicting BIST 100 Index Movement by using Sentiment Scores and Technical Indicators during the COVID-19 Pandemic

User2Vec: A Novel Representation for the Information of the Social Networks for Stock Market Prediction Using Convolutional and Recurrent Neural Networks

Prediction of Closing Stock Prices Using the Artificial Neural Network in the Market for Alternative Investment (MAI) of the Stock Exchange of Thailand (SET)

Contact Info

Product

Resources

About