Student Interest Performance Prediction Based On Improved Decision Support Vector Regression Using Machine Learning

The economic success of a government relies on the capability of its citizens to afford higher education. Ensuring maximum importance is given to this case is a crucial task for any government. However, the cost of education is affected by the amount of time students study before graduation. Moreover, one of the main obstacles facing universities is analyzing performance, proposing ways to improve the quality of education, and developing strategies to evaluate future practices. However, there is a lack of effectiveness and accuracy in standards for areas such as planning, leadership, online learning, student support, and assessment. To solve this problem, we use the Improved Decision Support Vector Regression (IDSVR) method to identify and determine the degree of quality verification for training schemes. Firstly, we used the Preferred Learning Materials Acquisition (PLMA) method to assess the similarity between student's learning and s behaviors. After that, the Lion and Krill Herd Optimization Algorithm (LKHOA) can be utilized to generate an efficient method for feature extraction. Finally, the IDSVR classification system can be used to identify and evaluate the level of quality assurance implementation in training programs based on Machine Learning (ML) techniques.