University Recommender System based on Student Profile using Feature Weighted Algorithm and KNN

This article removes the recommender structure for undergrad and graduate understudies which can help with picking the best schools matching their profile. The proposed model has used different extracting techniques for scrapping the data based on student profiles who have secured the seat successfully earlier. Then, machine learning technology is used to calculate the weighted scores based upon the training and testing data. This research study has introduced the KNN and Feature weighted algorithms to display the top N comparable clients for the test clients and recommend the Top M colleges to clients from the N comparative clients. As there is a colossal course of action of data and User profile, this research work is highly intended to use Knowledge-based techniques for two unmistakable models. Case-based information recommendation is used to calculate Graduate recommendations and constant-based recommendation is used for Undergraduate proposals.