University of Twente Student Theses
A Machine Learning Proposal for Predicting the Success Rate of IT-Projects Based on Project Metrics Before Initiation
Janssen, N.E. (2019) A Machine Learning Proposal for Predicting the Success Rate of IT-Projects Based on Project Metrics Before Initiation.
|
PDF
633kB |
| Abstract: | Thus far, the influence of information technology (IT) has grown tremendously with regards to all different aspects of today’s society. As a result, many IT-projects have been initiated however the success rates are rather limited. As a matter of fact, research has shown that approximately 1 out of 3 IT-projects fail. Over the years, a number of researchers started to examine predictive techniques to see to what extent it is possible to predict success. Various models are proposed, however until now, none of them is focused on predicting success before initiation. With the use of extensive literature research to critical success factors and project metrics, a new set of variables is given that is fully focused on IT-projects. Moreover, this set was validated through interviews with experts and a survey after which average importance scores were given to each critical success factor and metric. Lastly, general measurements are provided for each project metric that has a significant influence on the success of a project. This way, the conducted study provided a solid base for the development of a prediction model that will validate the results of this thesis once an appropriate dataset has been found. Therefore, this thesis serves as a guideline for future research on how to predict the success of IT-projects based on project metrics before initiation. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 85 business administration, organizational science |
| Programme: | International Business Administration BSc (50952) |
| Link to this item: | https://purl.utwente.nl/essays/78526 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page