Naïve Bayes classifier for optimizing personnel selection process in financial industry

Algorithmic human resources management (HRM) is becoming increasingly popular among organizations and many HRM processes include automated decision making HRM functions. Research is very active in the domain, and spans across machine learning and data mining, aiming to provide accurate methods to predict best candidates for job roles, or for personnel development among others. In this work, we present a Naïve Bayes based model, which focuses on the preliminary application screening steps, and suggest suitable applicants for further processing, based on a number of features. The model is presented, along with an application in a real case worked with a financial organization and using primary data selected from candidate applications. The results are promising and demonstrate that a mix of professional expertise along with algorithmic support may optimize the HMR processes.