Artificial Intelligence(AI), Machine Learning (ML) in The Demand Forecasting Process

Abusultan Rafiq (2023) Artificial Intelligence(AI), Machine Learning (ML) in The Demand Forecasting Process. Faculty of International Management and Business.

	PDF ARTIFICAL INTELLIGENCE(AI), MACHINE LEARNING (ML) IN THE DEMAND FORECASTING PROCESS _Final .v.5.pdf Hozzáférés joga: Available at the computers of the University Download (8MB)
	PDF Csonka 4 dissertation_report_external_RAbusultan_2023jan.pdf Hozzáférés joga: Bizalmas dokumentum (bírálat) Download (228kB)
	PDF Kerseztes 5 Abusultan, Rafiq dissertation_report_for_internal_advisors.pdf Hozzáférés joga: Bizalmas dokumentum (bírálat) Download (108kB)

Abstract

<p dir="ltr" style="text-align: left;">In most business entities, demand forecasting has become of great concern to help reduce operational costs, improve revenue, and increase customer satisfaction. Yet obtaining a more accurate and reliable demand forecast has been a great challenge for many business organisations. Most business organizations consider sharing data with their partners in the supply chain to enhance planning, efficiency, and accuracy. However, errors associated with forecasting can still lead to a significant rise in operational costs and a reduction in profits. Demand forecasting helps reduce the losses associated with the unpredictability of future demands. Many supply chains face challenges, especially the firms staged upstream of the chain. This suffering emanates from the variance amplification resulting from distortion in the information about demand from multi-stage supply chains, impacting operational efficiency. This study analyzed the various forms of demand forecasting and conducted a comparative analysis of the traditional and Artificial Intelligence (AI) techniques that can be used to predict future demands to assist business organisations minimize operational costs and improving revenue collection. The methodology employed by this study was a comparative analysis of the traditional forecasting method, and the AI or Machine Learning (ML) approaches. The study was guided by three research questions: 1. What improvements are expected from AI /Machine learning in the demand forecasting process 2 . How can machine learning be applied in demand forecasting 3. Which ML technique is more accurate and reliable in demand forecasting The study concludes that a hybrid system based on AI/ML is the best demand forecasting technique for most businesses to consider using to reduce operational costs, ensure customer satisfaction and improve revenue through accurate and efficient planning.<br></p>

Institution

Budapest Business University

Kar

Faculty of International Management and Business

Department

Társadalomtudományi Módszertan Tanszék

Tudományterület/tudományág

UNSPECIFIED

Szak

Nemzetközi gazdálkodás

Supervisors

Item Type:	Thesis (UNSPECIFIED)
Uncontrolled Keywords:	analysis, forecast, kereslet, mesterséges intelligencia, multinacionális vállalatok, network
SWORD Depositor:	Archive User
Depositing User:	Archive User
Date Deposited:	2023. Sep. 07. 14:25
Last Modified:	2023. Sep. 07. 14:25

Actions (login required)

View Item