Exploration of Feature Engineering Teaching Based on Max-Relevance Min-Redundancy

To meet the requirements of science and engineering personnel training in the new era, based on the teaching content of the feature engineering part of big data in the undergraduate teaching stage, combined with the process of machine learning practice, this paper discusses the course practice of the Max-Relevance Min-Redundancy algorithm in the task-driven Teaching mode. The study revolves around teaching content on feature engineering in big data during undergraduate education. Students practice algorithms in specific projects and accumulate practical experience in machine learning. They can better understand and apply the maximum correlation minimum redundancy algorithm to select feature variables, improve the performance of machine learning models, be familiar with the process of Feature Engineering, and improve students' ability to solve practical problems and employment competitiveness. The results of teaching practice show that the teaching practice has achieved a good teaching effect in improving students' practical ability and understanding and mastering of feature engineering.