Czasopismo
Tytuł artykułu
Autorzy
Treść / Zawartość
Pełne teksty:
![http://joim.pl/wp-content/uploads/2023/01/04-Journal-of-Intercultural-Management-162x230.pdf [zdalny]](images/mime-icons/pdf.gif "04-Journal-of-Intercultural-Management-162x230.pdf")
Warianty tytułu
Języki publikacji
Abstrakty
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 investors. Its 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. (original abstract)
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. (original abstract)
Czasopismo
Rocznik
Tom
Numer
Strony
63-78
Opis fizyczny
Twórcy
autor
- University of Lodz
Bibliografia
- Anghel, G. D. I. (2015). Stock Market Efficiency and the MACD. Evidence from Countries around the World. Procedia Economics and Finance, 32, 1414-1431.
- Bradley, D. A. (1984). Stock Market Prediction. The Planetary Barometer and How to Use It. Los Angeles: Llewellyn Publications.
- Czekaj, J., Woś, M., Żarnowski, J. (2001). Efektywność giełdowego rynku akcji w Polsce. Z perspektywy dziesięciolecia. Warszawa: Wydawnictwo PWN.
- Elder, A. (1993). Trading for a Living. Psychology. Trading Tactics. Money Management. New York: John Wiley & Sons Inc.
- Fernandes, R. A. S., & Mallqui Dennys, C. A. (2019). Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques. Applied Soft Computing, 75.
- Murphy, J. J. (2019). Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading Methods and Applications. New York: New York Institute of Finance.
- Rutkowski, L. (2005). Metody i techniki sztucznej inteligencji. Inteligencja obliczeniowa. Warszawa: Wydawnictwo Naukowe PWN.
- Stephenson, D. (2020). Big Data, nauka o danych i AI bez tajemnic. Gliwice: Wydawnictwo Helion.
- Szyszka, A. (2003). Efektywność giełdy papierów wartościowych w Warszawie na tle rynków dojrzałych. Poznań: Wydawnictwo Akademii Ekonomicznej w Poznaniu.
- Tarczyński, W. (2001). Rynki kapitałowe - metody ilościowe, vol. I. Warszawa: Placet, 2 ed.
- Torres, E. P., Hernández-Álvarez, M., Torres Hernández, E. A., & Yoo, S. G. (2019). Stock Market Data Prediction Using Machine Learning Techniques. In Á. Rocha, C. Ferrás, & M. Paredes (Eds.), Information Technology and Systems. ICITS 2019. Advances in Intelligent Systems and Computing, vol. 918. Springer.
- Wodecki, A. (2018). Sztuczna inteligencja w kreowaniu wartości organizacji. Kraków-Legionowo: Wydawnictwo Edu-Libri.
- www.asseco.com
- www.allegro.eu
- www.azure.microsoft.com/pl-pl/services/machine-learning
- www.ccc.eu
- www.cdprojekt.com
- www.gkpge.pl
- www.gpw.com.pl
- www.grupadino.pl
- www.jsw.pl
- www.kghm.com
- www.lppsa.com
- www.lotos.pl
- www.mercatormedical.eu
- www.orange.pl
- www.orlen.pl
- www.pekao.com.pl
- www.pgnig.pl
- www.pkobp.pl
- www.polsatbox.pl
- www.pzu.pl
- www.santander.pl
- www.tauron.pl
Typ dokumentu
Bibliografia
Identyfikatory
Identyfikator YADDA
bwmeta1.element.ekon-element-000171659520
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.