In this project, we developed a machine learning model that predicted student dropout rates or academic success based on a range of factors, such as attendance, grades, and demographic data. The goal was to identify students who were at risk of dropping out or falling behind and provide targeted interventions and support to help them succeed.
To create this model, we gathered data on the various factors that may affect a student's academic performance, including attendance records, grades, demographic information (such as age, gender, ethnicity, socioeconomic status, etc.), and any other relevant information that was available (such as extracurricular activities, health status, etc.).
Once we collected this data, we used it to train a machine learning algorithm to predict which students were at risk of dropping out or falling behind. The algorithm analyzed the data and identified patterns and trends that were indicative of poor academic performance or high dropout rates.
Once the algorithm was trained, we used it to identify students who were at risk of dropping out or falling behind and provided them with targeted interventions and support. This included offering additional tutoring or mentoring, providing counseling services, or connecting students with community resources that could help them succeed.
Overall, this project focused on using machine learning to improve student outcomes by identifying those who were at risk of dropping out or falling behind and providing them with the support and resources they needed to succeed.
Dataset collected from Kaggle - https://www.kaggle.com/code/stefansanchez26/students-dropout-prediction-with-logistic-reg
Original author of this dataset - https://zenodo.org/record/5777340#.ZEtLUXZBy3B