This project was developed as a part of IBM Hack Challenge 2023. This project tries to predict the outcome of a student's placement based on different parameters ( for example, their CGPA, number of backlogs, number of internships, etc). Our hope is that this project helps students to gauge their performance and work accordingly towards achieving a successful placements.
This comprehensive project revolves around the intricate world of campus placement data analysis, employing advanced machine learning techniques to uncover patterns and trends. The central goal is to craft a predictive model capable of scrutinizing diverse student attributes and forecasting their placement outcomes. This project encompasses a spectrum of data preprocessing, thorough exploratory data analysis (EDA), model development, rigorous evaluation, ensemble methodologies, and the culmination of deploying the model through an interactive web application. Our toolkit includes Python, an array of machine learning algorithms, scikit-learn, IBM Watson Studio, Flask, NumPy, Pandas, HTML, and JavaScript, all orchestrated to achieve our objectives.
- Predicts academic performance based on input parameters.
- Provides insights into students' academic success.
- Utilizes a variety of machine learning techniques for placement prediction.
- User-friendly web interface for input and prediction.
Follow these instructions to get the project up and running on your local machine.
- Python 3.x
- Flask
- NumPy
- Pandas
- Matplotlib
- Seaborn
- XGBoost
- scikit-learn
- Clone the repository:
git clone https://github.com/smartinternz02/SBSPS-Challenge-10169-1691067442.git- Navigate to the project directory:
cd SBSPS-Challenge-10169-1691067442- Install the required dependencies:
pip install Flask numpy requests- Open the MAIN CODE directory:
cd MAIN_CODE- Start the Flask web application using the following code:
python Placed_pred_main.py- Open a web browser and go to:
http://localhost:5000.Use the web interface to input student information and get predictions for academic performance.
You can reduce your work by just visiting our Placement Predictor webpage.
This project is licensed under the MIT License - see the LICENSE file for details.
Our heartfelt gratitude extends to the Mentors for their unwavering guidance and support throughout this remarkable journey. We also tip our hats to the tireless work of the open-source community and the indispensable tools and libraries they provided.