Adaptive talent journey: Optimization of talents’ growth path within a company via Deep Q-Learning

Abstract

In enterprise context, companies constantly aim to optimize their human resources and acquire new ones. Employees, also called talents, are required to achieve new skills for the company to stay competitive in the business. The talents’ ability to productively improve is a crucial factor for the success of a company.We propose Adaptive Talent Journey, a novel method for optimizing the growth path of talents within a company. The ultimate goal of Adaptive Talent Journey is to hold talent back inside the company. It exploits the notion of “digital twin” to define a digital representation of the talent, namely Talent Digital Twin, built on the basis of skills level and personal traits. Given a target company’s role, Adaptive Talent Journey proposes the most suitable path of work experiences (journey) to improve the skills of a talent so to achieve the target role requirements. Such a mechanism resonates with the Reinforcement Learning paradigm, and specifically with Deep Q-Learning. Specifically, the proposed method exploits: (i) two double Deep Q-Networks (DDQNs) for selecting the work experiences to be made; (ii) a transition module to support the DDQNs training and ensure good performance despite the limited availability of data.We implemented and deployed Adaptive Talent Journey in an intuitive Web application, namely ATJWeb. We evaluated both the effectiveness and efficiency of our proposal and the users’ satisfaction in using it, adopting, as a testbed, an IT company with its employees. Results proved that the Adaptive Talent Journey can optimize the growth path of talents, and that ATJWeb is pleasant and useful.