Enhancing Student Placement Predictions with a Trans-CLSTM Based Recommendation System

Enhancing students' employability poses a major hurdle for educational institutions in the present day, considering the intricate nature of educational entities. Institutions are finding ways to leverage technology in order to improve their administrative processes and decision-making capabilities. Providing comprehensive insights into educational processes and entities through advanced data analytics is crucial for a successful strategy. This study emphasises three crucial components: data preprocessing, feature selection, and model training. Data preprocessing is crucial for ensuring that the dataset is well-prepared for analysis. Various feature selection techniques are used to determine the most relevant features for training purposes. The proposed Trans-CLSTM models surpass traditional algorithms like LSTM and CNN, showcasing substantial enhancements in accuracy, achieving an impressive accuracy rate of 98.22%. This research adds to the ongoing efforts to improve educational quality and student outcomes using data-driven approaches.