TY - GEN
T1 - Development of project outcome prediction system for an IT vendor
AU - Kawamura, Tomoyuki
AU - Takano, Kenichi
PY - 2016/5/9
Y1 - 2016/5/9
N2 - Researchers have found that approximately 70% of information systems development projects in Japan have failed, thus increasing the demand for solutions that will raise expected project success rates. It is said that to improve success rates, it is essential that risk management should be conducted at an early stage. Although risk management is an important process that a project focuses on, it is difficult to mitigate the influence of all the risks through only the project. Therefore, it is noted that support should be provided by the organization to which the projects belong. The study aims to identify projects that an organization should support preferentially by predicting a project outcome that utilizes the assessment results of the project risks at an early stage. The risks of 88 projects of a Japanese IT vendor were assessed using a risk assessment sheet, and a project outcome prediction model was developed by utilizing the results of the assessment. As a consequence, a model with 73.9% predictive accuracy was obtained. It is thought that the system, including the risk assessment sheet and the project outcome prediction model, will contribute to identify projects that an organization should support preferentially.
AB - Researchers have found that approximately 70% of information systems development projects in Japan have failed, thus increasing the demand for solutions that will raise expected project success rates. It is said that to improve success rates, it is essential that risk management should be conducted at an early stage. Although risk management is an important process that a project focuses on, it is difficult to mitigate the influence of all the risks through only the project. Therefore, it is noted that support should be provided by the organization to which the projects belong. The study aims to identify projects that an organization should support preferentially by predicting a project outcome that utilizes the assessment results of the project risks at an early stage. The risks of 88 projects of a Japanese IT vendor were assessed using a risk assessment sheet, and a project outcome prediction model was developed by utilizing the results of the assessment. As a consequence, a model with 73.9% predictive accuracy was obtained. It is thought that the system, including the risk assessment sheet and the project outcome prediction model, will contribute to identify projects that an organization should support preferentially.
KW - Information systems
KW - Logistic regression analysis
KW - Project outcome prediction
UR - http://www.scopus.com/inward/record.url?scp=84974725596&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84974725596&partnerID=8YFLogxK
U2 - 10.1109/APSEC.2015.42
DO - 10.1109/APSEC.2015.42
M3 - Conference contribution
AN - SCOPUS:84974725596
T3 - Proceedings - Asia-Pacific Software Engineering Conference, APSEC
SP - 338
EP - 345
BT - Proceedings - 22nd Asia-Pacific Software Engineering Conference, APSEC 2015
A2 - Sun, Jing
A2 - Reddy, Y. Raghu
A2 - Bahulkar, Arun
A2 - Pasala, Anjaneyulu
PB - IEEE Computer Society
T2 - 22nd Asia-Pacific Software Engineering Conference, APSEC 2015
Y2 - 1 December 2015 through 4 December 2015
ER -