Abstract:
Entrepreneurship has been identified as the pillar of economic growth of any nation and is of high significance to small and medium enterprises (SMEs). There have been several efforts by the Nigerian government in the promotion of SMEs by providing training, internship, linkages to loans or grants, and business advisory services to her interested citizens. Selecting the beneficiaries among applicants is one of the major challenges being confronted. In recent times, machine learning techniques have been receiving growing attention and concern in a variety of research and application fields but not much scrutiny in contemporary entrepreneurship research. In this research, two machine learning algorithms C4.5 Decision tree and Naïve Bayes were modeled for entrepreneurship selection on a dataset collected from Entrepreneurship
Development Centre North-East, Maiduguri. Features ranking is carried out using the
information gain ratio approach. The Algorithms are implemented using python language
programing language. Skills acquired, existing business, educational qualification, and mental fitness are the first four ranked valuable features out of twenty available features. Comprehensive analysis shows that C4.5 outperformed Naïve Bayes with a prediction accuracy of 76.1% against 73.5% on selected features. The obtained results are encouraging and show the feasibility of machine learning approaches in entrepreneurship.
