ABSTRACT
While several comparative analyses between major international oil companies are widely available, the same cannot be said about oil companies from Central and Eastern Europe. The present study uses a power-set multilabel approach to analyze changes in the Romanian oil company SNP; stock prices in connection with its regional peers. The multilabel approach uses several base classifiers to analyze the data and a decision tree to choose among them for test purposes. This approach has more predictive power with respect to the area under the receiver operating characteristic ROC curve performance indicator and can be used to analyze other types of data.
Disclosure Statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
F. S. Duma
F. S. Duma is an Associate professor on Finance at the Babes-Bolyai University, with a PhD in Capital Markets. He was also every year invited as a guest professor or researcher at many different Universities all around Europe, but also in the United States, Korea, Vietnam etc. His main areas of research are finance, stock markets, big data and entrepreneurship.
R. I. Lung
R. I. Lung is currently a professor at the Department of Statistics, Forecasts, Mathematics within the Faculty of Economics and Business Administration, Babes-Bolyai University, Romania. She has a Bachelor’s degree in Mathematics (1998), a master’s degree in Convex Analysis and Optimization (1999), and a PhD in Computer Science (2006) from the same university. Her research interests include game theory, machine learning, statistics, and optimization.