USE OF DECISION TREES FOR PREDICTION OF PROJECT PERFORMANCE

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F16%3A86097898" target="_blank" >RIV/61989100:27510/16:86097898 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

USE OF DECISION TREES FOR PREDICTION OF PROJECT PERFORMANCE

Popis výsledku v původním jazyce

In today's changing world, the project management risks have to be taken into account by all project focused organizations. One big risk associated with project is a risk of project failure. To increase likelihood of project success, it is important to be able to identify drivers of success. Big advantage of decision trees is possibility of identification the importance of variables. Decision makers have thus a powerful tool in their hands and can determine which project characteristics are important for project success and can focus efforts of project team on them. Another advantage of decision trees is the easiness of visualization, implementing into existing systems and understanding by non-technical people. Decision trees are simply a set of IF-THEN rules. In this study decision trees are used to predict success of development projects of the World Bank. The most important variables identified are Overall Bank Performance, Overall Borrower Performance, Bank Quality of Supervision, Bank Quality at Entry, Implementing Agency Performance and Government Performance. Other variables play only a minor role. Performance of predictive decision tree model was high with accuracy 93.13 % and specificity 89.17 %, so the benefit of decision tree usage was proven.

Název v anglickém jazyce

USE OF DECISION TREES FOR PREDICTION OF PROJECT PERFORMANCE

Popis výsledku anglicky

In today's changing world, the project management risks have to be taken into account by all project focused organizations. One big risk associated with project is a risk of project failure. To increase likelihood of project success, it is important to be able to identify drivers of success. Big advantage of decision trees is possibility of identification the importance of variables. Decision makers have thus a powerful tool in their hands and can determine which project characteristics are important for project success and can focus efforts of project team on them. Another advantage of decision trees is the easiness of visualization, implementing into existing systems and understanding by non-technical people. Decision trees are simply a set of IF-THEN rules. In this study decision trees are used to predict success of development projects of the World Bank. The most important variables identified are Overall Bank Performance, Overall Borrower Performance, Bank Quality of Supervision, Bank Quality at Entry, Implementing Agency Performance and Government Performance. Other variables play only a minor role. Performance of predictive decision tree model was high with accuracy 93.13 % and specificity 89.17 %, so the benefit of decision tree usage was proven.

Druh

D - Stať ve sborníku

CEP obor

AE - Řízení, správa a administrativa

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IDIMT-2016 : Information Technology, Society and Economy Strategic Cross-Influences : 24th Interdisciplinary Information Management Talks : Sept. 7-9, 2016, Poděbrady, Czech Republic

ISBN

978-3-99033-869-8

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

375-381

Název nakladatele

Trauner

Místo vydání

Linz

Místo konání akce

Poděbrady

Datum konání akce

7. 9. 2016

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

000387756100042