Fake Profile Detection using Machine Learning

A machine learning project that detects fake social media profiles using Neural Network, Random Forest, and Support Vector Machine classifiers.

This project was developed as an academic/cloud-computing mini-project demonstrating practical implementation of the underlying research concept using a Java/JSP web stack backed by MySQL.

• Neural Network, Random Forest, and SVM classification models
• Fake vs. genuine user dataset (fusers.csv, users.csv)
• Exported HTML/PDF reports of model results
• Reusable, well-documented notebooks per model

• Python
• Jupyter Notebook
• scikit-learn
• pandas
• NumPy

1. Prerequisites

   • JDK 8 or higher
   • Apache Tomcat 8/9
   • MySQL Server 5.7+
   • An IDE such as NetBeans or Eclipse (recommended for legacy JSP/Servlet projects)

2. Clone the repository

   git clone https://github.com/cloudurga/fake-profile-detection-ml.git
   cd fake-profile-detection-ml

3. Set up the database

   • Create a MySQL database.
   • Import the provided .sql file (if present under a Database/DATABASE folder) using:

     mysql -u root -p your_database_name < path/to/database.sql

   • Update the JDBC connection details (host, username, password, database name) in the project's DB connection file (e.g. connect.jsp / DBCon.jsp / db.properties).

4. Deploy

   • Open the project in NetBeans/Eclipse.
   • Configure the Apache Tomcat server.
   • Build and deploy the project (or copy the compiled WAR to Tomcat's webapps directory).

1. Start MySQL and Apache Tomcat.
2. Access the application in your browser, typically at:

   http://localhost:8080/fake-profile-detection-ml/
   

3. Log in using the admin/user credentials configured in the database, and navigate the application modules described above.

Fake-Profile-Detection-using-ML-master/
  data/
    fusers.csv
    users.csv
  html/
    Neural Network.html
    Random Forest.html
    Support Vector Machine.html
  pdf/
    Neural_Network.pdf
    RandomForest.pdf
    SVM.pdf

(Structure trimmed to top levels for readability — see the repository for the full file listing.)

• Migrate the legacy JSP/Servlet stack to a modern framework (e.g. Spring Boot) with a REST API backend
• Containerize the application with Docker for simplified deployment
• Add automated unit and integration tests
• Replace raw JDBC with an ORM (e.g. Hibernate/JPA) for safer data access
• Improve UI/UX with a modern responsive frontend framework

This project is licensed under the MIT License. See the LICENSE file for details.

Documentation generated and repository structured by an automated DevOps assistant, 2026.