A Neural Network Approach to Selection of Candidates for Electoral Offices by Political Parties

摘要

Useful governance comes from a reliable electoral process. Such begins from candidate selection within political parties. In Nigeria, factors such as electoral system, party ideology, political culture, and the organization of government, overtime had influenced candidates’ selection processes for the conduct of political party primaries invariably make it subjective. Thus candidates who make it through such process are not always the party’s best. Invariably, many of these candidates loose the general elections. Obviously, advancement in technology has gradually changed nearly every facet of live yet there exist exceptions in the area of democratizing the electoral system. In this paper, we present a feed forward/back propagation neural network based approach to selecting suitable candidates for elective positions before general elections. We had to enlarge the training dataset through interpolative synthesis. Our result proved that the approach was efficacious. In this report, we present an introduction to the problem and the methodology of solving the problem. Thereafter, we reported on the design, implementation and the results obtained from the system. We drew useful conclusions were later drawn from the results.