Thesis (MEng)--Stellenbosch University, 2003. / ENGLISH ABSTRACT: Whenever projects fail, analysis of the causes has shown that risks were present from day one.
Often individuals at some level in the project team have knowledge of these risks and they could
have been identified and appropriate remedial action taken. Risk, whether identified or not,
generally results in some increase in financial exposure on behalf of the organisation, but, if
managed well, offers a potential that could lead to increased profits.
There has been a tremendous explosion regarding the amount of data that organisations
generate, collect and store. Managers are beginning to recognize the value of this asset and are
increasingly relying on intelligent systems to access, analyse, summarise and interpret
information from large and multiple data sources. These systems help them to make critical
decisions at a faster rate or with a greater degree of confidence. Data mining is a promising new
technology that helps bring intelligence into these systems.
The purpose of this thesis is to present a methodology that integrates a data mining technique
with a decision support system in order to form an intelligent decision support system. The
implementation of such an intelligent decision support system will enable project and project risk
managers to improve the management of and reduce risk within a project.
This thesis consists of two sections. The first section describes the processes and characteristics
of project management, project risk management, data mining and decision support systems. The
aim is to provide the reader with a background about these four management methodologies. The
second section describes the methodology of how the processes of project and project risk
management can benefit from the integration of a data mining technique and a decision support
system.
An application that uses the case-based reasoning approach as a data mining technique to
intelligently profile a project according to its risks is demonstrated. / AFRIKAANSE OPSOMMING: Wanneer projekte misluk, toon 'n analise van die oorsake dat risiko's vanuit die staanspoor daar
teenwoordig was. Individuele persone op verskillende vlakke in die projekspan is dikwels daarvan
bewus. Hierdie risiko's kon geïdentifiseer gewees het en regstellende stappe kon geneem
gewees het. Risiko, hetsy geïdentifiseer of nie, loop gewoonlik uit op 'n sekere mate van toename
in finansiële blootstelling namens die organisasie, maar wanneer dit goed bestuur word, bied dit
'n potensiaal vir verhoogde wins.
Daar is 'n geweldige vermeerdering in die hoeveelheid data wat organisasies genereer, versamel
en berg. Bestuurders begin alreeds die onskatbare waarde van hierdie bate besef en steun
toenemend op intelligensiestelsels vir toegang, analise, opsomming en interpretasie van inligting
van omvangryke en veelsoortige databronne. Hierdie sisteme stel hulle in staat om kritieke
besluite vinniger of met 'n groter mate van vertroue te neem. Dataontginning is 'n belowende
nuwe tegnologie wat daartoe bydra dat intelligensie in hierdie sisteme ingebring word.
Die doel van hierdie tesis is om 'n metodologie wat 'n dataontginningstegniek met 'n
besluitnemingsondersteuningsisteem integreer sodat 'n intelligente besluitnemingsondersteuningsisteem
gevorm kan word. Die implementering van so 'n intelligensie
besluitnemingsondersteuningsisteem sal projekbestuurders en projekrisikobestuurders in staat
stelom die bestuur van 'n projek te verbeter en die risiko binne die projek te verminder.
Hierdie tesis word in twee dele aangebied. Die eerste deel beskryf die prosesse en
karakteristieke van projekbestuur, projekrisikobestuur, dataontginning en
besluitondersteuningsisteme. Sodoende word aan die leser agtergrondinligting van hierdie vier
bestuursmetodologieë verskaf. Die tweede deel beskryf die metodologie en hoe die prosesse van
projekbestuur en projekrisikobestuur voordeel kan trek uit die integrasie van 'n
dataontginningstegniek en 'n besluitondersteuningsisteem.
'n Toepassing is ontwikkel wat die gevallebasis beredeneringsbenadering as 'n dataontginingstegniek gebruik om 'n projek op 'n intelligente wyse volgens sy risiko's uit te beeld.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:sun/oai:scholar.sun.ac.za:10019.1/53470 |
| Date | 12 1900 |
| Creators | Loftus, Kennith |
| Contributors | Fourie, C. J., Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. |
| Publisher | Stellenbosch : Stellenbosch University |
| Source Sets | South African National ETD Portal |
| Language | en_ZA |
| Detected Language | Unknown |
| Type | Thesis |
| Format | 86 p. : ill. |
| Rights | Stellenbosch University |
Page generated in 0.0023 seconds