Given the dataset of Clearwater State University's student information, a column contains data about student's early attrition is taken as target and an end-to-end machine learning model is built using 'Random Forest Classification' algorithm which has accuracy of 84%.
Clearwater State University has collected student data to check the enrolment to the curriculum programs and the percentage of students continuing to the next year. It was observed that many students are opting out from continuing the next year. The rate of attrition was very high.
Here, the goal is to,
1. Identify key drivers of early student attrition,
2. Build a predictive model to identify students with higher attrition risk,
3. Recommend appropriate interventions based on analysis.
- Data Acquisition
- Exploratory Data Analysis
- Data Visualization
- Data Preprocessing
- Model Building
- Model Evaluation