Pregled bibliografske jedinice broj: 1086351
Evaluation of Alternative Approaches in Classification Algorithms for Prediction of Stock Market Index
Evaluation of Alternative Approaches in Classification Algorithms for Prediction of Stock Market Index // Recent Applications of Financial Risk Modelling and Portfolio Management / Škrinjarić, Tihana ; Čižmešija, Mirjana ; Christiansen, Bryan (ur.)., 2020. str. 204-221 doi:10.4018/978-1-7998-5083-0.ch010
CROSBI ID: 1086351 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Evaluation of Alternative Approaches in
Classification Algorithms for Prediction of Stock
Market Index
Autori
Vlah Jerić, Silvija
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Recent Applications of Financial Risk Modelling and Portfolio Management
Urednik/ci
Škrinjarić, Tihana ; Čižmešija, Mirjana ; Christiansen, Bryan
Izdavač
IGI Global
Godina
2020
Raspon stranica
204-221
ISSN
2327-5677
Ključne riječi
Day Trading, Classification Problem, Neural Network, Support Vector Machine, Random Forest, K-Nearest Neighbors, Naïve Bayes, Crobex
Sažetak
This chapter tackles the problem of automatic recognition of favorable days for intra-day trading. The problem is modeled as a binary classification problem and several approaches are tested for solving it. Croatian stock index CROBEX data is used and 22 technical indicators are calculated as predictor variables. Performance of five classifiers is evaluated and compared by using Cohen’s kappa as evaluation metric: artificial neural network, support network machine, random forest, k-nearest neighbors and naïve Bayes classifier. The results give insight to effectiveness of technical analysis in predicting the day favorability for CROBEX index and suggest that technical analysis makes sense and might work for this case.
Izvorni jezik
Hrvatski
Znanstvena područja
Matematika, Računarstvo, Ekonomija
