Improveing Agent-based modelling by using machine learning

Agent-based modelling (ABM) is increasingly being used as a way of understanding complex phenomena and systems. As traditional agent-based modelling relies on the designer's knowledge of the model, this thesis focuses on methods to improve the accuracy of traditional ABM using machine learning...

Full description

Bibliographic Details
Main Author: Shen, Xin
Format: Dissertation (University of Nottingham only)
Language:English
Published: 2022
Subjects:
Online Access:https://eprints.nottingham.ac.uk/70226/
_version_ 1848800608815939584
author Shen, Xin
author_facet Shen, Xin
author_sort Shen, Xin
building Nottingham Research Data Repository
collection Online Access
description Agent-based modelling (ABM) is increasingly being used as a way of understanding complex phenomena and systems. As traditional agent-based modelling relies on the designer's knowledge of the model, this thesis focuses on methods to improve the accuracy of traditional ABM using machine learning (ML). Firstly, a traditional ABM is developed using Counter-Strike: Global Offensive as the subject of study, followed by data mining using linear regression and k-mean clustering to develop an ML-based ABM. Finally, k nearest neighbours is used to measure the accuracy of the traditional ABM and the ML-based ABM. The results show that the traditional ABM achieve 78.8% accuracy and the ML-based ABM accuracy improve by 14.07% accuracy to 92.95%. This demonstrates the difficulty in achieving a high level of accuracy in the traditional way of modelling ABM, which will result in less accurate simulations of ABM. Machine learning can help researchers to better understand the characteristics of the target model in order to achieve a higher level of accuracy.
first_indexed 2025-11-14T20:54:16Z
format Dissertation (University of Nottingham only)
id nottingham-70226
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:54:16Z
publishDate 2022
recordtype eprints
repository_type Digital Repository
spelling nottingham-702262023-06-30T13:13:03Z https://eprints.nottingham.ac.uk/70226/ Improveing Agent-based modelling by using machine learning Shen, Xin Agent-based modelling (ABM) is increasingly being used as a way of understanding complex phenomena and systems. As traditional agent-based modelling relies on the designer's knowledge of the model, this thesis focuses on methods to improve the accuracy of traditional ABM using machine learning (ML). Firstly, a traditional ABM is developed using Counter-Strike: Global Offensive as the subject of study, followed by data mining using linear regression and k-mean clustering to develop an ML-based ABM. Finally, k nearest neighbours is used to measure the accuracy of the traditional ABM and the ML-based ABM. The results show that the traditional ABM achieve 78.8% accuracy and the ML-based ABM accuracy improve by 14.07% accuracy to 92.95%. This demonstrates the difficulty in achieving a high level of accuracy in the traditional way of modelling ABM, which will result in less accurate simulations of ABM. Machine learning can help researchers to better understand the characteristics of the target model in order to achieve a higher level of accuracy. 2022-09-08 Dissertation (University of Nottingham only) NonPeerReviewed application/pdf en https://eprints.nottingham.ac.uk/70226/1/Msc_Dissertation_Xin_Shen.pdf Shen, Xin (2022) Improveing Agent-based modelling by using machine learning. [Dissertation (University of Nottingham only)] Agent-based modelling machine learning linear regression clustering k nearest neighbours
spellingShingle Agent-based modelling
machine learning
linear regression
clustering
k nearest neighbours
Shen, Xin
Improveing Agent-based modelling by using machine learning
title Improveing Agent-based modelling by using machine learning
title_full Improveing Agent-based modelling by using machine learning
title_fullStr Improveing Agent-based modelling by using machine learning
title_full_unstemmed Improveing Agent-based modelling by using machine learning
title_short Improveing Agent-based modelling by using machine learning
title_sort improveing agent-based modelling by using machine learning
topic Agent-based modelling
machine learning
linear regression
clustering
k nearest neighbours
url https://eprints.nottingham.ac.uk/70226/