The Application of Algorithm Optimization and Big Data Processing in Higher Education Management

Big data processing and algorithm optimization techniques, which include machine learning and optimization algorithms, have tremendous scope for the enhancement of different functions of university management. They would improve decision-making, teaching quality, and resource allocation toward better student results. It investigates how these technologies can be used in higher education, with specific attention to teaching quality monitoring and resource optimization. It uses a teaching quality dataset compiled from student ratings, faculty performance metrics, and course completion rates, as well as resource allocation data like classroom occupancy and faculty schedules. The preprocessing of the data includes the handling of missing values and the normalization of numerical data. Techniques for feature extraction, such as principal component analysis, are used to reduce the dimensionality of teaching quality indicators. It combines binary Runge–Kutta optimizer tuned multi-layer perceptron to analyze the teaching quality indicators and provide improvement recommendations. Multi-criteria decision analysis helps optimize resource distribution, which may include faculty time, classroom space, and educational materials. The proposed approach, using Python (v3.11), achieves high performance, with accuracy (95.83%), recall (96.71%), and mean absolute percentage error (1.0213%). The evaluation process is efficient which takes only 12.3 s. The model also provides valuable insights into how resources can be better managed, helping universities to make more informed decisions. With an overall confidence rate of 97.31% and an enhancement rate of 92.56%, the findings show that big data and algorithm optimizations can significantly improve teaching quality and resource management in higher education.