Recurrent academic path recommendation model for engineering students using MBTI indicators and optimization enabled recurrent neural network.

In recent years, the rapid expansion of online learning content has made it increasingly difficult for students to identify suitable educational pathways. This challenge is particularly significant for engineering students, who often require structured guidance to select appropriate academic courses. To address this issue, an intelligent recommendation model is proposed that assists students in discovering the most suitable academic path based on their personal background and personality traits. A hybrid optimization-based deep recurrent neural network (DRNN) with Myers-Briggs Type Indicator (MBTI) is presented for Recurrent Academic Path Recommendation (RAPR) for engineering students. At first, the data transformation is applied considering the log kernel to improve data quality. Then, the Sparse Fuzzy C-Means Clustering (Sparse FCM) is employed to choose imperative features. At last, an adaptive recommendation of the engineering department is performed using DRNN, which is trained based on the Magnetic Invasive Weed Optimization (MIWO) algorithm. On the other hand, MBTI personality type categorization is done, wherein the correlation of courses with MBTI outcome is detected using MIWO-based DRNN. The evaluation is conducted using two datasets, which are the collected academic information of students from Kerala and Tamilnadu. These datasets include the details, such as students' personality traits, Science, Technology, Engineering, and Mathematics performance, extra-curricular involvement, MBTI weight test, and MBTI score. The performance of the proposed MIWO-based DRNN is evaluated using precision, recall, and F-measure metrics and the proposed method offers the best performance with the highest precision of 0.900, recall of 0.900, and F-measure of 0.899, demonstrating its effectiveness in accurately recommending academic paths for engineering students.