Forecasting the investors behavior on the capital market in Romania: Trading strategies based on technical analysis versus Artificial Intelligence techniques

Authors

  • Gabriela Victoria Anghelache Professor, Department of Money and Banking Bucharest University of Economic Studies, Romania
  • Alina Lucia Trifan Ph.D. Assistant, Department of Money and Banking Bucharest University of Economic Studies, Romania

DOI:

https://doi.org/10.18533/ijbsr.v3i2.79

Keywords:

financial time series forecasting, trading strategies, artificial neural networks, fuzzy logic, neuro-fuzzy systems

Abstract

This research aims at characterizing and modelling the investors’ behaviours present on the Romanian capital market, by analyzing the behaviours proposed by the efficient markets theory and investigating the possibility of financial time series behaviour forecasting through artificial intelligence concepts and tools (artificial neural networks, fuzzy logic, neuro-fuzzy systems).

 

The analysis of various forecasting strategies has been conducted using data sets on a daily basis, on a time horizon of nine years, for a total of 22 companies listed on BSE and for the BET and BET-C exchange indexes; the research is differentiating the pre-crisis period and the crisis period.

 

Downloads

Issue

Vol. 3 No. 2 (2013): February

Section

Article

License

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).