A Model for Mapping Graduates’ Skills to Industry Roles: Machine Learning Architecture
This paper presents a machine learning architecture of a hierarchical model for mapping skills to industry roles. Currently, researchers have been approaching the problem of selecting industry roles for potential employees using flat and top-down methods. Practically, top-down approach is not reliable because it negates the natural mobility of employees in the occupational industry role hierarchy while flat approach does not take advantage of not only the easier learning property of hierarchical approach but also the local information of parent child relationship for better results. The machine learning architecture has been an attempt to address this gap using experimental research design. The mapping model consists of a collection of objects that are hierarchically arranged to progressively group industry role constructs before applying bottom-up approach to select the best. The mapping begins by first selecting the most promising sub-objects at the lower levels before passing this information to the higher levels of the hierarchy to select the most promising functional (main competence), proficiency and specialty (specific competence) objects and eventually the respective constructs. The end product is an effective machine learning architecture of a model for mapping graduates’ skills to industry roles with relevant attributes to easily work with in the academia and that correctly reflects the hierarchy of industry roles. Findings reveal while SVM (67%) optimizes the model’s accuracy better than naïve Bayes (57%), on the same benchmark dataset the model recorded better performance (85%) than reported performance (82%) in the benchmark model. The findings will benefit industry by getting evaluation tool for revealing information on graduate’s suitability for employment which they can use for decision making when filtering candidates for interview. Besides, this will provide researchers better understanding of the gap between the academia and industry and can use this information to plan on how to bridge the gap using the mapping model. Lastly, this will attempt to reduce both low job satisfaction and long-term unemployment that is one of the causes of social and economic pain both in Kenya and around the world. However, this paper recommends testing this approach with other alternative machine learning techniques as well as other alternative industry domains.