Planiranje potražnje uz pomoć strojnog učenja

master's thesis

• Title (english): Demand Forecasting using Machine Learning
• Author: Marija Matijević
• Mentor: Kristijan Rogić (mentor)
• Committee member: Ratko Stanković (predsjednik povjerenstva)
• Committee member: Darko Babić (član povjerenstva)
• Committee member: Ivona Bajor (član povjerenstva)
• Granter: University of Zagreb; Faculty of Transport and Traffic Sciences; (Division of Intelligent Transport Systems and Logistics); (Department of Transport Logistics); Zagreb
• Defense date and country: 2020-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Traffic and Transport Technology; Intelligent Transport Systems and Logistics

Abstract

Visoka učinkovitost opskrbnog lanca može se postići primjenom odgovarajućih metoda za dugoročno predviđanje prognoze. Klasične metode prognoze jednostavne su u svome izračunu, ali njihova točnost zna biti na nezavidnoj razini. Stoga su metode strojnog učenja dobra prilika za poboljšanje ovoga polja. Ovaj rad donosi usporedbu prognoze potražnje klasičnom metodom sezonalnog autoregresivnog integriranog pomičnog prosjeka s vanjskim varijablama te metodama strojnog učenja, metoda slučajne šume i metoda umjetne neuronske mreže.

Abstract (english)

High efficiency of the supply chain can be attained by applying the bestperforming methods for long term forecasting. Traditional forecasting methods are easy to implement and compute but their accuracy can be lackluster. Therefore, methods that implement machine learning are a great way to improve this field. This paper compares forecast results using three methods, one of them is a classic method of the autoregressive integrated moving average with external variables, the other two methods are machine learning methods, random forest regression, and artificial neural networks.

• Keywords: prognoza potražnje; strojno učenje; sezonalni autoregresivni integrirani pomični prosjek s vanjskim varijablama; slučajna šuma; umjetna neuronska mreža
• Keywords (english): demand forecasting; machine learning; seasonal autoregressive integrated moving average with external variables; random forest regressor; artificial neural network
• Language: croatian
• URN:NBN: urn:nbn:hr:119:335677
• Study programme: Title: Intelligent Transport Systems and Logistics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka prometa (magistar/magistra inženjer/inženjerka prometa)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-11-27 13:02:32