Language:

STOCK PRICE PREDICTION AT ZAGREB STOCK EXCHANGE: MULTILAYER PERCEPTRON AND SUPPORT VECTOR MACHINE

Proceedings of FEB Zagreb International Odyssey Conference on Economics and Business, 2022, Vol.4 (1), p.755-768

Full text available

Citations Cited by

Title:
STOCK PRICE PREDICTION AT ZAGREB STOCK EXCHANGE: MULTILAYER PERCEPTRON AND SUPPORT VECTOR MACHINE
Author: Bach, Mirjana Pejić ; Jelić, Hrvoje ; Medić, Tomislav
Subjects: Algorithms ; Artificial intelligence ; Deep learning ; Forecasting ; Machine learning ; Neural networks ; Prices ; Software packages ; Stock exchanges ; Support vector machines
Is Part Of: Proceedings of FEB Zagreb International Odyssey Conference on Economics and Business, 2022, Vol.4 (1), p.755-768
Description: This paper investigates the benefits of applying a novel approach to time series analysis using machine learning models in the context of stock price prediction. To achieve this goal, we apply two different machine learning models, Multilayer Perceptron and Support Vector Machine, to predict the prices of the five most traded stocks on the Zagreb Stock Exchange. Stock prices used for building, training, and testing the model were retrieved from Zagreb Stock Exchange. Weka is a machine learning software developed in Java used to test the performance of the proposed machine learning models. Using the models mentioned above, we tried to determine if machine learning has a relevant potential for forecasting future prices of stocks traded on the Zagreb Stock Exchange.
Publisher: Zagreb: University of Zagreb, Faculty of Economics and Business
Language: English
Identifier: ISSN: 2671-132X
Source: ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Searching Remote Databases, Please Wait