Predicting Stock Return and Volatility With Machine Learning and Econometric Models: A Comparative Case Study of the Baltic Stock Market

Nõu, Anders; Lapitskaya, Darya; Eratalay, Mustafa Hakan; Sharma, Rajesh

doi:10.2139/ssrn.3974770

Cited by 4 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learns the model using the training dataset, then the predictions made with the learned model are compared with the test dataset, and the results are evaluated [ 46 ]. In similar studies in the literature, datasets have been divided into different ratios such as 75:25, 78.6:21.4, 90:10, 60:40, 80:20, 83:17, and 70:30 [ 18 , 29 , 30 , 36 , 41 , 44 , 45 ]. Although no general opinion exists about the ratio into which the data be divided, it is recommended to use the ratio of 80:20 in classification processes for large datasets [ 47 ].…”

Section: Datasetmentioning

confidence: 99%

“…Since the early 2000s, the application of Machine Learning Models (MLMs) in stock predictions has enabled the analysis and prediction of large volumes of data with higher accuracy [ 17 ]. Consequently, the development of machine learning models and algorithms in this context has facilitated both effective and efficient decision-making processes, enabling instant and highly predictive outcomes [ 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

How effective is machine learning in stock market predictions?

Ayyildiz,

Iskenderoglu

2024

Heliyon

View full text Add to dashboard Cite

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

How effective is machine learning in stock market predictions?

Ayyildiz,

Iskenderoglu

2024

Heliyon

View full text Add to dashboard Cite

“…This particularly holds true for statistical, pattern recognition, machine learning, and sentiment analysis approaches, alongside some hybrid techniques. There is no unequivocal voice among scholars and practitioners about the best approach, since some authors advocate statistical (see Islam and Nguyen 2020) whereas other advocate for machine learning approaches (see Singh et al 2017, Nõu et al 2023.…”

Section: Athens Journal Of Technology and Engineeringmentioning

confidence: 99%

Untitled

2024

AJTE

View full text Add to dashboard Cite

ATINER is an independent and non-profit Association with a Mission to become a forum where Academics and Researchers from all over the world can meet in Athens, exchange ideas on their research and discuss future developments in their disciplines, as well as engage with professionals from other fields. Athens was chosen because of its long history of academic gatherings, which go back thousands of years to Plato's Academy and Aristotle's Lyceum. Both these historic places are within walking distance from ATINER's downtown offices. Since antiquity, Athens was an open city. In the words of Pericles, Athens"…is open to the world, we never expel a foreigner from learning or seeing". ("Pericles' Funeral Oration", in Thucydides, The History of the Peloponnesian War). It is ATINER's mission to revive the glory of Ancient Athens by inviting the World Academic Community to the city, to learn from each other in an environment of freedom and respect for other people's opinions and beliefs. After all, the free expression of one's opinion formed the basis for the development of democracy, and Athens was its cradle. As it turned out, the Golden Age of Athens was in fact, the Golden Age of the Western Civilization. Education and (Re)searching for the 'truth' are the pillars of any free (democratic) society. This is the reason why Education and Research are the two core words in ATINER's name.

show abstract

“…The results indicated that the random forests algorithm provided the most successful outcomes, followed by support vector machines, artificial neural networks, k-nearest neighbors, and logistic regression algorithms. Nou et al (2015) aimed to predict returns and volatilities in the OMX Baltic Benchmark price index of the Baltic Stock Exchange. Daily closing data from September 4, 2001, to March 1, 2021, were used, and predictions for the index's direction were made using random forests, support vector machines, and k-nearest neighbors algorithms.…”

Section: 2studies On the Directional Prediction Of Stock Market Indic...mentioning

confidence: 99%

Prediction of Stock Market Index Movements with Machine Learning

Ayyıldız

2023

View full text Add to dashboard Cite

The book titled "Prediction of Stock Market Index Movements with Machine Learning" focuses on the performance of machine learning methods in forecasting the future movements of stock market indexes and identifying the most advantageous methods that can be used across different stock exchanges. In this context, applications have been conducted on both developed and emerging market stock exchanges. The stock market indexes of developed countries such as NYSE 100, NIKKEI 225, FTSE 100, CAC 40, DAX 30, FTSE MIB, TSX; and the stock market indexes of emerging countries such as SSE, BOVESPA, RTS, NIFTY 50, IDX, IPC, and BIST 100 were selected. The movement directions of these stock market indexes were predicted using decision trees, random forests, k-nearest neighbors, naive Bayes, logistic regression, support vector machines, and artificial neural networks methods. Daily dataset from 01.01.2012 to 31.12.2021, along with technical indicators, were used as input data for analysis. According to the results obtained, it was determined that artificial neural networks were the most effective method during the examined period. Alongside artificial neural networks, logistic regression and support vector machines methods were found to predict the movement direction of all indexes with an accuracy of over 70%. Additionally, it was noted that while artificial neural networks were identified as the best method, they did not necessarily achieve the highest accuracy for all indexes. In this context, it was established that the performance of the examined methods varied among countries and indexes but did not differ based on the development levels of the countries. As a conclusion, artificial neural networks, logistic regression, and support vector machines methods are recommended as the most advantageous approaches for predicting stock market index movements.

show abstract

Predicting Stock Return and Volatility With Machine Learning and Econometric Models: A Comparative Case Study of the Baltic Stock Market

Cited by 4 publications

References 42 publications

How effective is machine learning in stock market predictions?

How effective is machine learning in stock market predictions?

Untitled

Prediction of Stock Market Index Movements with Machine Learning

Contact Info

Product

Resources

About