Title: Project outcome classification with imprecise criteria information

Authors: Rueben Laryea

Addresses: Department of Computer and Systems Sciences, Stockholm University, Forum 100, 16440, Kista, Stockholm, Sweden

Abstract: A case in which managers have to make project outcome classification decisions with uncertainty in independently related criteria values is considered in this paper. A multi-criteria decision model is developed in this paper by selecting methods which delved into data analysis to help managers make informed classification decisions. Uncertainty in the criteria values is resolved using linear programming which enables managers to know the profit outcome of their projects for efficient resource allocation. The classification scheme from the linear programming process is used as predefined classification inputs for use in the UTilités Additives DIScriminantes (UTADIS) method, which further produces a classification model. The analysis presented a no misclassification error in the predefined classifications from the linear programming and the classifications in the UTADIS method thus further boosting the confidence managers can entrust in the resulting classification model.

Keywords: multicriteria decision making; MCDM; modelling; classification models; project outcomes; imprecision: linear programming; project outcome classification; imprecise criteria; uncertainty.

DOI: 10.1504/IJADS.2013.056867

International Journal of Applied Decision Sciences, 2013 Vol.6 No.4, pp.372 - 387

Available online: 13 Sep 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article