Primjena strojnog učenja u predviđanju otkazivanja hotelskih rezervacija

master's thesis

• Title (english): Application of Machine Learning to Hotel Reservation Cancellations
• Author: Pavle Pavišić
• Mentor: Tomislav Burić (mentor)
• Committee member: Tomislav Burić (predsjednik povjerenstva)
• Committee member: Josipa Pina Milišić (član povjerenstva)
• Committee member: Lenka Mihoković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad usmjeren je na primjenu strojnog učenja u svrhu predviđanja otkazivanja hotelskih rezervacija. Na taj način upravljački sloj hotela ostvaruje veću fleksibilnost u pogledu upravljanja vlastitim resursima te izbjegava negativne posljedice otkazivanja čime je postignut cilj rada. Nakon početnog poglavlja o strojnom učenju i osnovnim algoritmima, slijedi praktični dio rada. Počevši od opisa podataka, nakon čišćenja i eksploratnorne analize podaci su pripremljeni za treniranje. Treniranje je provedeno koristeći nekoliko različitih algoritama i postignuta je zadovoljavajuća točnost. Nakon analize modela, rezultati su uspoređeni te su analizirani mogući razlozi krivih predikcija.

Abstract (english)

This paper focuses on the application of machine learning for the purpose of predicting the cancellation of hotel reservations. Being able to predict cancellations, hotel management layer achieves greater flexibility in terms of managing its own resources, but also avoids the negative consequences of cancellation, which is the primary goal of this work. After initial chapter on machine learning and its basic algorithms, paper continues on with the practical part. Starting from the description of the data, after cleaning and exploratory analysis, the data was prepared for training. The training was conducted using several different algorithms and satisfying accuracy was achieved. After analyzing the model, the results were compared and the possible reasons for the wrong predictions were analyzed.

• Keywords: strojno učenje; eksploratorna analiza; otkazivanje rezervacija; hotel; korelacija značajki; klasifikacija; preciznost
• Keywords (english): machine learning; exploratory analysis; reservation cancellation; hotel; feature correlation; classification; precision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:704231
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 15:48:41