Student Marks Prediction
An interactive Machine Learning web application that predicts student marks based on user-provided information.

The project demonstrates how data science and machine learning can be combined with Streamlit to turn a prediction model into a simple, interactive web application.

About the Project
Student performance can be influenced by several factors. This project explores how data can be used to build a predictive model for estimating a student’s marks.

Instead of keeping the machine-learning model inside a notebook or Python script, I created an interactive Streamlit interface that allows users to enter information and receive a predicted result.

This project helped me understand the complete basic machine-learning workflow:

Data → Analysis → Model → Prediction → Interactive Web App

Features
Uses data to make predictions about student performance
Applies machine-learning concepts
Accepts user input interactively
Generates a predicted student mark
Provides a simple web-based interface
Gives predictions instantly
Deployed online using Streamlit
Technologies Used
Python
Streamlit
Data Science
Machine Learning
Pandas
Scikit-learn
How It Works
The application follows a simple prediction pipeline:

User Input
↓
Data Processing
↓
Machine Learning Model
↓
Prediction
↓
Predicted Student Marks
Users enter the required information through the Streamlit interface. The application processes the values and sends them to the trained prediction model.

The model then calculates an estimated score and displays the prediction to the user.

Try the App
https://student-marks-prediction-ilina-k-sri-yoeftkx66b55vgcqhvteea.streamlit.app/

No installation is required to use the online version.

What I Learned
Through this project, I developed experience with:

preparing data for machine-learning tasks
understanding relationships between variables
building a prediction workflow
using Python for data science
working with machine-learning models
accepting and processing user input
connecting a model to a web interface
creating interactive applications with Streamlit
deploying a data-science project online
One of the most useful lessons from this project was learning that a machine-learning model becomes much more accessible when users can interact with it through a simple interface.