Kvantitativna istraživanja Zagrebačke
burze

Šego, Boško; Škrinjarić, Tihana

doi:10.32910/ep.69.6.3

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Naime, navedena tržišta dionica su još uvijek nedovoljno analizirana u literaturi (Škrinjarić, 2022). Kako na tim tržištima i dalje dominiraju neki čimbenici specifični za pojedine zemlje, njihovim uključivanjem u portfelj može se postići veća diversifikacija (Karkowska & Urjasz, 2022;Özer, Kamenković & Grubišić, 2020;Šego & Škrinjarić, 2018;Cevik, Korkmaz & Cevik, 2017). Također, prethodna istraživanja (Škrinjarić, 2018;Ferreira, 2018) pokazala su predvidljivost promjena vrijednosti indeksa na ovim tržištima, dugoročnu zavisnost prinosa na indekse, što podržava odbacivanje slabog oblika efikasnosti.…”

Section: Uvodunclassified

Analysis of the Financial Performance of Machine Learning Models for Predicting the Direction of Changes in Cee and See Stock Market Indices With Different Classification Evaluation Metrics

Vlah Jerić

2023

Ekonomska misao i praksa

View full text Add to dashboard Cite

Cilj analize je istražiti utjecaj odabira metrike za vrednovanje klasifikatora na financijsku uspješnost sustava trgovanja temeljenih na modelima strojnog učenja za burzovne indekse iz zemalja CEE i SEE regija. Tehničkim indikatorima se koriste kao značajke za odabrane algoritme strojnog učenja pri predviđanju smjera promjena vrijednosti indeksa, tj. klasificiranje dana trgovanja u dvije klase. Istraživanje je pokazalo da odabir metrike za vrednovanje klasifikatora nema veliki utjecaj na financijsku uspješnost takvog sustava, no ipak su najveći prosječni prinosi po transakciji postignuti maksimizacijom točnosti. Nadalje, algoritam slučajne šume i naivni Bayesov klasifikator dali su najveće prosječne prinose korištenjem točnosti, dok su stroj potpornih vektora i algoritam k najbližih susjeda najveće prosječne prinose postigli pri korištenju površine ispod krivulje operativnih karakteristika. Utvrđeno je da očekivano veliki utjecaj na financijsku uspješnost ima odabir algoritma za strojno učenje te da algoritam slučajne šume daje najbolje rezultate na ovim podacima.

show abstract

Section: Uvodunclassified

Analysis of the Financial Performance of Machine Learning Models for Predicting the Direction of Changes in Cee and See Stock Market Indices With Different Classification Evaluation Metrics

Vlah Jerić

2023

Ekonomska misao i praksa

View full text Add to dashboard Cite

show abstract

CEE and SEE equity market return spillovers: Creating profitable investment strategies

Škrinjarić

2020

Borsa Istanbul Review

View full text Add to dashboard Cite

Comparing classification algorithms for prediction on CROBEX data

Jerić

2020

Croatian Review of Economic, Business and Social Statistics

View full text Add to dashboard Cite

The main objective of this analysis is to evaluate and compare the various classification algorithms for the automatic identification of favourable days for intraday trading using the Croatian stock index CROBEX data. Intra-day trading refers to the acquisition and sale of financial instruments on the same trading day. If the increase between the opening price and the closing price of the same day is substantial enough to earn a profit by purchasing at the opening price and selling at the closing price, the day is considered to be favourable for intra-day trading. The goal is to discover relation between selected financial indicators on a given day and the market situation on the following day i.e. to determine whether a day is favourable for day trading or not. The problem is modelled as a binary classification problem. The idea is to test different algorithms and to give greater attention to those that are more rarely used than traditional statistical methods. Thus, the following algorithms are used: neural network, support vector machine, random forest, as well as k-nearest neighbours and naïve Bayes classifier as classifiers that are more common. The work is an extension of authors’ previous work in which the algorithms are compared on resamples resulting from tuning the algorithms, while here, each derived model is used to make predictions on new data. The results should add to the increasing corpus of stock market prediction research efforts and try to fill some gaps in this field of research for the Croatian market, in particular by using machine learning algorithms.

show abstract

Kvantitativna istraživanja Zagrebačke burze

Cited by 5 publications

References 12 publications

Analysis of the Financial Performance of Machine Learning Models for Predicting the Direction of Changes in Cee and See Stock Market Indices With Different Classification Evaluation Metrics

Analysis of the Financial Performance of Machine Learning Models for Predicting the Direction of Changes in Cee and See Stock Market Indices With Different Classification Evaluation Metrics

CEE and SEE equity market return spillovers: Creating profitable investment strategies

Comparing classification algorithms for prediction on CROBEX data

Contact Info

Product

Resources

About