Utilizing Machine Learning to Optimize the Data-Driven Talent Cultivation of Higher Education in the Digital Age

This paper explores the methods and practices of utilizing machine learning (ML) to optimize data-driven talent cultivation in higher education in the digital age. With the advent of the digital age, higher education is facing an increasing amount of data and a complex learning environment. Traditional teaching models can no longer meet the personalized learning needs of students. To address this challenge, the paper proposes a personalized learning path planning method based on Deep Reinforcement Learning (DRL), aiming to optimize the teaching process of higher education, improve student learning efficiency and grades. This method will combine students’ personalized learning needs and the distribution of teaching resources, and intelligently design learning paths, so that each student can achieve the expected learning goals in the shortest time. Through the intelligent analysis and optimization of students’ learning behavior and learning process, students’ learning efficiency and grades can be improved, and the overall improvement of teaching quality can be promoted. This study is of great significance to promote the digital transformation and intelligent development of higher education, and provides new ideas and support for the reform and innovation of higher education in the future.