Rudarjenje asociativnih pravil v poslovnih aplikacijah

magistrsko delo

Aljaž Lipar (Author), Iztok Fister (Mentor), Damijan Novak (Co-mentor)

Abstract

V magistrski nalogi smo obravnavali tehniko, poimenovano rudarjenje asociativnih pravil, katere namen je odkrivanje in podrobno razumevanje skritih vzorcev v podatkih. Odkrite skrite vzorce pa predstavljajo asociativna pravila, ki se pri tem postopku ustvarijo in služijo kot smernice za priporočanje izdelkov ali produktov, optimizacijo zalog in analizo nakupovalnih navad. Predstavili smo tudi, kaj so optimizacijski algoritmi, ki jih rudarjenje asociativnih pravil uporablja, in kako delujejo. Velik poudarek smo podali tudi na personalizacijo, kaj je, kakšne vplive ima na ljudi, prav tako pa smo podali par praktičnih primerov. Nato smo opisali orodja, ki smo jih uporabljali, podrobneje predstavili uARMSolver ter kako ga vzpostaviti in uporabiti. Nato smo opisali našo izdelano rešitev, na koncu pa opravili še analizo ter interpretacijo rezultatov.

Keywords

algoritem;asociativna pravila;diferencialna evolucija;personalizacija;rudarjenje;magistrske naloge;

Data

Language:	Slovenian
Year of publishing:	2025
Typology:	2.09 - Master's Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[A. Lipar]
UDC:	004.62.021(043.2)
COBISS:	229529859
Views:	0
Downloads:	17
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Association rule mining in business applications
Secondary abstract:	In this master's thesis, we discussed a technique called association rule mining, the purpose of which is the discovery and detailed understanding of hidden patterns in data. The discovered hidden patterns represent the associative rules created in this process and serve as guidelines for recommending products, optimizing stocks and analyzing shopping habits. We also learned and presented what the optimization algorithms used by associative rule mining are and how they work. We also put a lot of emphasis on personalization, what it is, and what effects it has on people, and we also gave a couple of practical examples. We then described the tools we used, introduced uARMSolver in more detail and showed how to set it up and use it. Then we described our developed solution, and at the end, we performed an analysis and interpretation of the results.
Secondary keywords:	algorithm;association rules;differential evolution;personalization;mining;master's theses;
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in podatkovne tehnologije
Pages:	1 spletni vir (1 datoteka PDF (59 f.))
ID:	25786491