prikaz prve stranice dokumenta Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije
  Download
PDF 676.84 KB
master's thesis
Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije
2020. urn:nbn:hr:126:321705
Crnobrnja, Martina
Josip Juraj Strossmayer University of Osijek
Department of Mathematics
Chair of Applied Mathematics and Computer Science

Cite this document

Crnobrnja, M. (2020). Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:321705

Crnobrnja, Martina. "Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:321705

Crnobrnja, Martina. "Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2020. https://urn.nsk.hr/urn:nbn:hr:126:321705

Crnobrnja, M. (2020). 'Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije', Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 22 December 2024, https://urn.nsk.hr/urn:nbn:hr:126:321705

Crnobrnja M. Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2020 [cited 2024 December 22] Available at: https://urn.nsk.hr/urn:nbn:hr:126:321705

M. Crnobrnja, "Modeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije", Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:126:321705

Please login to the repository to save this object to your list.
Metadata
TitleModeliranje odljeva igrača u online klađenjima primjenom neuronskih mreža i logističke regresije
Title (english)Customer Churn Prediction in the Online Gambling using Neural Networks and Logistic Regression
AuthorMartina Crnobrnja
MentorNataša Šarlija (mentor)
Committee memberMirta Benšić (predsjednik povjerenstva)
Committee memberNataša Šarlija (član povjerenstva)
Committee memberNenad Šuvak (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
(Chair of Applied Mathematics and Computer Science)
Osijek
Defense date and country2020-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Applied Mathematics and Mathematical Modeling
Abstract
Online tržište igara na sreću vrlo je profitabilno. Zbog velike konkurentnosti važno je efektivno zadržati klijente. Svrha predikcije odljeva klijenata je na temelju ponašanja u prošlosti identificirati klijente koji će s velikom vjerojatnošću prestati s klađenjem kod priredivaća igara na sreću. Cilj rada je usporediti modeliranje odljeva neuronskom mrežom s prihvaćenim statističkim modelom logističke regresije. U prvom dijelu rada objašnjene su struktura i učenje neuronske mreže. U drugom dijelu rada predstavljeni su generalizirani linearni modeli i logistička regresija. Obzirom na vrstu modela, međusobno su uspoređeni rezultati tri modela neuronske mreže i tri modela logističke regresije. Nakon toga uspoređen je model neuronske mreže s modelom logističke regresije. Model neuronske mreže ostvario je bolje rezultate od modela logističke regresije.
Abstract (english)
The online gambling industry is one of the most profitable branches of the entertainment business. Intense competition makes it very important to effectively retain clients. The purpose of churn prediction is to identify clients with high probability to leave online gambling company based on their past behavior. The aim of this thesis is to critically compare a neural network technique with the established statistical technique of logistic regression for churn prediction. In the first part of the thesis, structure and learning of neural networks were explained. In the second part we introduced generalized linear models and logistic regression. After creating three models using neural networks and three models using logistic regression, the results were compared within techniques. After that, comparison across techniques was made. It was shown that neural network model performed better than logistic regression model.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:321705
Study programmeTitle: Mathematics; specializations in: Financial and Statistical Mathematics, Mathematics and Computer Science, Industrial and Applied Mathematics
Course: Financial and Statistical Mathematics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-10-02 06:57:36