Simplification of Decision Rules for Recommendation of Projects in a Public Project Portfolio
In this paper, we propose the use of decision rules to aid in the recommendation of a portfolio of public projects. A decision table indicates what decisions should be made when the condition attributes are satisfied. Projects can be modeled as decision tables, where the characteristics of the projects are condition attributes and the qualification of each project is the decision attribute. Reducing the decision rules, we can give a simple explanation of why a certain project has its qualification; this simplification is a useful procedure because most decision problems can be formulated in a decision table. Public portfolio problem, due to its nature, has been approached by multi-criteria algorithms, which generate a set of solutions in the Pareto frontier. The selection of a portfolio depends on the decision maker, so the simplified decision rules can help him/her to analyze why a project have been added to a certain portfolio and justify the final selection.
This work was partially financed by CONACYT, COTACYT, DGEST, TECNM, and ITCM.
- 1.Labreuche, C., Maudet, N., Ouerdane, W.: Minimal and complete explanations for critical multi-attribute decisions. In: Algorithmic Decision Theory, pp. 121–134. Springer, Berlin, Heidelberg (2011)Google Scholar
- 2.Ouerdane, W., Dimopoulos, Y., Liapis, K., Moraitis, P.: Towards automating decision aiding through argumentation. J. Multi Criteria Decis. (2011)Google Scholar
- 4.Fernández-González, E., Vega-Lopez, I., Navarro-Castillo, J.: Public portfolio selection combining genetic algorithms and mathematical decision analysis. In: Bio-Inspired Computational Algorithms and Their Applications, pp. 139–160 (2012)Google Scholar
- 6.Skowron, A., Grzymal, J.: From rough set theory to evidence theory. In: Yager, R.R., Kacprzyk, J., Fedrizzi, M. (eds.) Advances in the Dempster-Shafer theory of evidence, pp. 193–236. Wiley, New York (1994)Google Scholar
- 7.Düntsch, I., Gediga, G.: Rough set data analysis. Encycl. Comput. Sci. Technol. 43(28), 281–301 (2000)Google Scholar
- 9.Stefanowski, J.: Changing representation of learning examples while inducing classifiers based on decision rules. Artificial Intelligence Methods, AI-METH (2003)Google Scholar
- 11.Wroblewski, J.: Finding minimal reducts using genetic algorithms. In: Proceedings of the 2nd annual join conference on information science, pp. 186–189, Sept, 1995Google Scholar
- 12.Newman, D.J., Hettich, S., Blake, C.L., Merz, C.J.: UCI repository of machine learning databases. University of California, Irvine, Department of information and computer sciences (1998), http://www.ics.uci.edu/~mlearn/MLRepository.html