We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Destek Vektör Makineleri ile Borsa Endekslerinin Tahmini.
- Authors
KARTAL, Cem
- Abstract
Support Vector Machines (SVM) is one of the most popular machine learning algorithms. In this study, it is aimed to use SVM, which is one of the leading stock indices of the world together with BIST100 index and a machine learning technique in the classification of return directions of S&P 500, DAX and NIKKEI 225 indices. Besides, it is aimed to reveal the estimation (classification) performances of these techniques. For this purpose, SVMs have been used to model the "upward" and "downward" trends of stock market indices. In addition, the effects of macroeconomic variables on stock market indices are analysed. The data set of the study includes 82 observational values of dependent and independent variables monthly between 01.01.2013- 30.11.2019. 70 (85%) of these observation values are used for modelling (training) and 12 (15%) for classification (test). As a result of the study, it is found that the model shows success in upward forecasts, but it does not show the same success in downward forecasts.
- Subjects
NIKKEI 225; SUPPORT vector machines; STANDARD &; Poor's 500 Index; STOCK price indexes; STOCK exchanges; BUSINESS forecasting
- Publication
Itobiad: Journal of the Human & Social Science Researches / İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 2020, Vol 9, Issue 2, p1394
- ISSN
2147-1185
- Publication type
Article
- DOI
10.15869/itobiad.673015