Repository containing code for The Third Leap, in fulfillment of the requirement for DCIT 307, offered at the University of Ghana
# StudentSuccessAI
This project involves analyzing student performance data using machine learning techniques. The aim is to build a model that can predict if a student is likely to pass or fail based on various attributes such as family background, study habits, and other demographic factors.
- **Link to App** -
the-third-leap-studentsucce…
- **Link to Youtube Presentation**
- Part 1:
youtu.be
- Part 2:
youtu.be
The repository has 2 branches
- **main** - This contains the notebooks and data used in training the model, as well as the trained model.
- **Interface** - This contains the Streamlit interface developed to host the code.
## Dataset
The dataset used for this project is the Student Performance Dataset from Kaggle. This dataset contains information on student grades in Mathematics and Portuguese language courses, as well as various demographic and social factors that may influence their performance.
## Description of files in Repository
- **StudentSuccessAI** - This contains the initial analysis done on the dataset, as well as the different encoding techniques tried on the data.
- **student_final(1)** - This notebooks builds on results of the analysis performed on **StudentSuccessAI**. It works on improving the accuracy of the model built.
- **student_final(2)** - This is the final notebook. It contains the improved model pipeline, saving the complete model to a file for later use.
- **student-data.csv** - This is the data on which the model was trained.
- **trained_model.sav** - This is the final trained model that will be used
## Conclusion
This project demonstrates how machine learning techniques can be used to analyze student performance data and predict a student's likelihood of passing or failing. The project also highlights the importance of data preprocessing and feature selection in building an accurate machine learning model. The project shows that using …