This is a data science project in which an algorithm is created to distinguish dropout students from Graduate and Enrolled students. The dataset includes numerous variables that are used to train the data for student categorization. The main phases include data cleaning, exploratory data analysis, and implementing a machine learning algorithm.
This dataset provides a detailed view on students academic performance based on their demographics, social and economic status. All the information mentioned above is taken at the time of admission. This project is focused on measuring student academic success based on different factors such as application mode and demographics. Additionally, curricular units (credited/enrolled/evaluations/approved) and grades provided at the end of the semester can further assist in the betterment of the analysis and implementation of the algorithm. Finally, factors like GDP, employment rate and inflation rate can also be used to make the analysis better by providing context for economic factors. This dataset is provided by UCI Machine learning repository. The link to the dataset is:
- Importing Required Libraries
- Data Ingestion
- Data Overview
- Data Cleaning
- Exploratory Data Analysis
- Algorithm Selection and Implementation
- Results and Discussions
- Conclusion