1. Pre-processed student and teacher datasets, handling missing values and inconsistent data. 2. Standardized time availability columns to match between datasets. 3. Constructed a K-means model and allocated data points to the nearest cluster. 4. Generated recommendations for students based on clusters, considering location, instrument, and availability hours. 5. Identified the town with the highest clustering, indicating a high success rate of matching students with teachers.
Apr 01, 2023 - May 31, 2023