Data-driven Adaptive Personalized Property Investment Risk Analysis: Frameworks, Methods and System

Demong, Nur Atiqah Rochin

Data-driven Adaptive Personalized Property Investment Risk Analysis: Frameworks, Methods and System

Demong, Nur Atiqah Rochin

Permalink

Publication Type:: Thesis
Issue Date:: 2020

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (3.39 MB)

Adobe PDF

Download thesisAdobe PDF (8.47 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Demong, Nur Atiqah Rochin
dc.date.accessioned	2021-03-16T23:46:59Z
dc.date.available	2021-03-16T23:46:59Z
dc.date.issued	2020
dc.identifier.uri	http://hdl.handle.net/10453/147267
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US
dc.description.abstract	The risk analysis for real estate property investment which incurred a high cost and high risk has been qualitatively and quantitatively assessed by various techniques. These techniques consider the heuristic risk factors mainly based on the expert survey, weigh and rank the factors using algorithms and mathematical formulas and decide the best investment based on the performance index of alternatives given. Currently, identifying, weighing, and ranking of the risk factors in investment decisions largely depend on expert judgment using traditional approaches. Additionally, current research is lacking in considering investors’ different preferences and requirements. The motivation of this study is how to identify, weigh and rank the risk analysis factors when experts have a different point of view or judgments’ and expert subjective justifications. This thesis describes a new personalized multidimensional process (PMP) framework based on knowledge discovery to overcome the weaknesses of existing risk identification and measurement techniques. This framework comprises two new methods namely personalized association mapping (PAM) method and personalized multidimensional sensitivity analysis (PM-SA) method. This thesis also proposes an adaptive personalized property investment risk analysis (APPIRA) method to identify the property investment determinants. This APPIRA method adopts a data-driven and personalization technique to weigh risk factors and ranking using a multi-criteria decision-making model by applying the TOPSIS method for optimal solutions. The existing real estate analytic systems, which only serve as search tools and do not benefit homebuyers in terms of search time, flexibility, and intuitive results. Thus, a prototype of adaptive personalized property investment risk analysis system (APPIRAS) developed to validate the framework and methods proposed to overcome the limitations. The innovations of this research were the justification of risk factor identification as the determinant for different objectives; weighing which is based on historical data-driven to decision support using the knowledge discovery approach (analytical decision-making) and the investor’s adaptive personalization of the risk factors which fulfil their requirements; and ranking using multi-criteria decision-making model. The methodology in this research incorporated literature review, frameworks development, methods development, prototype software system development and evaluation. A case study has been developed to show the applicability of the developed framework, methods, and system. The outcomes of this study have a significant impact in helping investors to achieve their objectives and APPIRAS as the decision support tools to achieve optimal decisions. These methods can be applied to practice and benefit the property industry directly.	en_US
dc.format	Thesis (PhD)
dc.language.iso	en	en_US
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/147267/2/02whole.pdf
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Data-driven Adaptive Personalized Property Investment Risk Analysis: Frameworks, Methods and System	en_US
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

The risk analysis for real estate property investment which incurred a high cost and high risk has been qualitatively and quantitatively assessed by various techniques. These techniques consider the heuristic risk factors mainly based on the expert survey, weigh and rank the factors using algorithms and mathematical formulas and decide the best investment based on the performance index of alternatives given. Currently, identifying, weighing, and ranking of the risk factors in investment decisions largely depend on expert judgment using traditional approaches. Additionally, current research is lacking in considering investors’ different preferences and requirements. The motivation of this study is how to identify, weigh and rank the risk analysis factors when experts have a different point of view or judgments’ and expert subjective justifications. This thesis describes a new personalized multidimensional process (PMP) framework based on knowledge discovery to overcome the weaknesses of existing risk identification and measurement techniques. This framework comprises two new methods namely personalized association mapping (PAM) method and personalized multidimensional sensitivity analysis (PM-SA) method. This thesis also proposes an adaptive personalized property investment risk analysis (APPIRA) method to identify the property investment determinants. This APPIRA method adopts a data-driven and personalization technique to weigh risk factors and ranking using a multi-criteria decision-making model by applying the TOPSIS method for optimal solutions. The existing real estate analytic systems, which only serve as search tools and do not benefit homebuyers in terms of search time, flexibility, and intuitive results. Thus, a prototype of adaptive personalized property investment risk analysis system (APPIRAS) developed to validate the framework and methods proposed to overcome the limitations. The innovations of this research were the justification of risk factor identification as the determinant for different objectives; weighing which is based on historical data-driven to decision support using the knowledge discovery approach (analytical decision-making) and the investor’s adaptive personalization of the risk factors which fulfil their requirements; and ranking using multi-criteria decision-making model. The methodology in this research incorporated literature review, frameworks development, methods development, prototype software system development and evaluation. A case study has been developed to show the applicability of the developed framework, methods, and system. The outcomes of this study have a significant impact in helping investors to achieve their objectives and APPIRAS as the decision support tools to achieve optimal decisions. These methods can be applied to practice and benefit the property industry directly.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/147267