prikaz prve stranice dokumenta Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a
Access restricted to students and staff of home institution
master's thesis
Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a
2017. urn:nbn:hr:145:621349
Babić, Darija
Josip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
Chair of Quantitative Methods and Informatics

Cite this document

Babić, D. (2017). Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:145:621349

Babić, Darija. "Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:145:621349

Babić, Darija. "Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:145:621349

Babić, D. (2017). 'Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, accessed 15 November 2024, https://urn.nsk.hr/urn:nbn:hr:145:621349

Babić D. Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek; 2017 [cited 2024 November 15] Available at: https://urn.nsk.hr/urn:nbn:hr:145:621349

D. Babić, "Neuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, Osijek, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:145:621349

Please login to the repository to save this object to your list.
Metadata
TitleNeuronske mreže i stabla odlučivanja za predviđanje cijene dionica Kraš-a
Title (english)NEURAL NETWORKS AND DECISION TREES FOR PREDICTION STOCK PRICES KRAŠ
AuthorDarija Babić
MentorMarijana Zekić Sušac (mentor)
Committee memberMarijana Zekić Sušac (predsjednik povjerenstva)
Committee memberĐula Borozan (član povjerenstva)
Committee memberNataša Šarlija (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
(Chair of Quantitative Methods and Informatics)
Osijek
Defense date and country2017-09-06, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Rad se bavi kreiranjem neuronske mreže i stabla odlučivanja kao i od analize neuronske mreže i analize stabla odlučivanja u svrhu predviđanja cijena dionica Kraš-a. Model je kreiran s ulaznim varijablama kao što su cijena otvaranja i cijena zatvaranja dionice na određeni dan, najniže i najviše cijene dionice na određeni dan, prosječne cijene dionice za određeni dan, promjene cijene u odnosu na prethodni dan, broja obavljenih transakcija, količine prodanih dionica, ukupnog prometa za dan, ekonomičnosti ukupnog poslovanja, rentabilnosti imovine te koeficijentom obrta ukupne imovine. Za izlaznu varijablu korištena je cijena zatvaranja dionice sljedeći dan koja je podijeljena u 3 grupe (niska, srednja, visoka). Pomoću programskog paketa Statistica dobiveni su i opisani rezultati. Za izradu modela neuronske mreže koristile su se logistička aktivacijska funkcija i tangens aktivacijska funkcija. Dobiveni rezultati pokazali su da logistička i tangens aktivacijska funkcija imaju jednaku stopu točnosti (77,08%), dok stablo odlučivanja generira stopu točnosti od 100%, stoga se pokazalo kao uspješniji model.
Abstract (english)
The work is about creating neural network and decision tree, but also about the analysis of neural network and decision tree for the purpose of predicting Kraš stock prices. The model is created using input variables such as the price of an opening stock and the price of a closing stock for a certain day, the highest and the lowest stock prices on a particular day, average stock prices for a particular day, changes of the price regarding to the previous day, numbers of the processed transactions, quantity of the selled stocks, total traffic for a day, cost-effectiveness of total business, rentability of assets and trade coefficient of total assets. The price of the closing stock the next day, divided into three groups (low, medium, high), was used as an output variable. The results were given and described with the help of software package Statistica. Logistic activation function and tangent activation function were used for making a model of the neural network. The given results showed that logistic and tangent activation function have the same accuracy rate (77,08%), while decision tree generates the accuracy rate at 100%. Decision tree has proved to be a more successful model.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:145:621349
Study programmeTitle: Business economy; specializations in: Business Informatics
Course: Business Informatics
Study programme type: university
Study level: graduate
Academic / professional title: Magistar/magistra ekonomije (Magistar/magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2017-10-10 14:51:14