Minimizacija kreditnog rizika uporabom neuroevolucije u dubokom učenju

undergraduate thesis

• Title (english): Minimization of credit risk using neuroevolution in deep learning
• Author: Luka Nestić
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: David Dukić (član povjerenstva)
• Committee member: Josip Jukić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-05, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Procjena kreditnog rizika jedan je od glavnih problema s kojima se susreću banke i kreditne kuće. U novije doba umjetne inteligencije nerijetko se za rješavanje ovakvih problema koriste duboke neuronske mreže, a jedan od postupaka optimizacije takvih mreža je uporaba biološki inspiriranih metaheurističkih algoritama, drugim nazivom neuroevolucija. U okviru ovog rada su ukratko opisane osnove konvencionalne neuroevolucije i dubokog učenja te evolucijskih algoritama potrebnih za rješavanje problema. Ispitani su i optimizirani algoritmi evolucijske strategije i diferencijske evolucije nad skupom podataka za smanjenje kreditnog rizika te je provedena njihova međusobna usporedba.

Abstract (english)

Credit risk assessment is one of the main problems faced by banks and credit institutions. In recent times, artificial intelligence has often been used to solve such problems using deep neural networks. One of the optimization approaches for such networks is the use of biologically inspired metaheuristic algorithms, also known as neuroevolution. This paper briefly describes the fundamentals of conventional neuroevolution, deep learning, and evolutionary algorithms required for solving such problems. The algorithms of evolution strategies and differential evolution have been tested and optimized on a dataset for credit risk minimization, and their mutual comparison has been conducted.

• Keywords: neuroevolucija; duboko učenje; predvid̄anje odobrenja kredita; umjetne neuronske mreže; evolucijski algoritmi
• Keywords (english): neuroevolution; deep learning; loan approval prediction; artificial neural networks; evolutionary algorithms
• Language: croatian
• URN:NBN: urn:nbn:hr:168:532643
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 09:55:17