Optimizacijski pristupi rješavanju problema alokacije prostora na policama

master's thesis

• Title (english): Optimization approaches in shelf-space allocation problem
• Author: Maja Klepo
• Mentor: Branimir Novoselnik (mentor)
• Committee member: Branimir Novoselnik (predsjednik povjerenstva)
• Committee member: Mario Vašak (član povjerenstva)
• Committee member: Anita Banjac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-09-22, Croatia

Abstract

Problem raspodjele prostora na policama odnosi se na određivanje koliko prostora treba dodijeliti svakom proizvodu na polici s ciljem povećanja profitabilnosti. U radu je definiran problem alokacije prostora na policama, opisani su različiti pristupi optimizacije prostora na policama te je predstavljen objedinjeni pristup koji sažima sva prethodna istraživanja. Poseban naglasak stavljen je na predviđanje potražnje proizvoda, gdje su opisani tradicionalni pristupi i pristupi strojnog učenja. Implementirani su modeli ekstremnog gradijentnog pojačavanja i dugog kratkoročnog pamćenja te su prikazani i uspoređeni njihovi rezultati.

Abstract (english)

The shelf space allocation problem refers to determining how much space should be allocated to each product on the shelf, in order to increase profitability. In this thesis, shelf space allocation problem is described, as well as different shelf space optimization approcahes and unique approach that summarizes all previous research. Special emphasis is placed on product demand forecasting, where traditional and machine learning approaches are presented. Extreme gradient boosting model and long short-term memory model are implemented and the results are presented and compared.

• Keywords: problem raspodjele prostora na policama; optimizacija; učinci potražnje; eksponencijalno izglađivanje; ARIMA; pojačavanje gradijenta; dugo kratkoročno pamćenje
• Keywords (english): shelf space allocation problem; optimization; demand effects; exponential smoothing; ARIMA; gradient boosting; long short-term memory
• Language: croatian
• URN:NBN: urn:nbn:hr:168:897767
• 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: 2024-03-28 07:48:44