Integrating Machine Learning And Mathematical Optimization For Skill-Centric Talent Acquisition

The increasing demand for skilled professionals in dynamic digital labor markets has exposed significant limitations in traditional recruitment systems, which often rely on resumes and subjective evaluation criteria. These methods frequently fail to capture candidates' true competencies, resulting in inefficient hiring decisions and suboptimal talent utilization. This study proposes an integrated framework that combines machine learning techniques with mathematical optimization to enable skill-centric talent acquisition. The objective is to develop a robust, data-driven hiring model that emphasizes measurable performance and objective evaluation. The proposed system leverages machine learning algorithms to analyze job requirements, extract relevant skill features, and generate customized evaluation tasks aligned with real-world problem scenarios. Candidates are assessed based on their ability to solve these tasks, ensuring that recruitment decisions are grounded in practical competency rather than self-reported qualifications. The evaluation process incorporates multiple performance indicators, including solution accuracy, logical reasoning, efficiency, and quality of implementation. These parameters are quantified and used as inputs to a mathematical optimization model designed to rank candidates and identify the best match for a given role. A key contribution of this work is the formulation of an optimization framework that maximizes skill compatibility between candidates and job requirements while minimizing hiring time and evaluation bias. By integrating predictive analytics with optimization techniques, the system enhances decision-making accuracy and ensures consistency in candidate selection. Furthermore, the framework supports scalability and adaptability, making it suitable for diverse recruitment scenarios, particularly in freelance and project-based environments. The results demonstrate that the integration of machine learning and mathematical optimization significantly improves recruitment efficiency, transparency, and fairness. The proposed approach reduces reliance on subjective judgment, streamlines the screening process, and promotes merit-based hiring practices. leading to improved project outcomes and workforce productivity. Additionally, it facilitates better alignment between organizational needs and candidate capabilities, leading to improved project outcomes and workforce productivity. In conclusion, this study establishes a comprehensive methodology for intelligent, skill-focused recruitment by bridging the gap between artificial intelligence and mathematical modeling. The proposed framework provides a scalable and objective solution for modern talent acquisition challenges, with potential applications in online hiring platforms, corporate recruitment systems, and digital freelancing ecosystems.