Skip to content
View mohitrajjj's full-sized avatar
1 follower · 0 following

Block or report mohitrajjj

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mohitrajjj/README.md

Mohit Raj

MCA graduate from RV College of Engineering (CGPA 7.90, First Class with Distinction), with a background in full-stack development, machine learning, and data analytics. I like taking an idea from concept to a working product — most of what's below started as a coursework requirement and turned into something I kept building on after the grade was in.

Currently looking for an entry-level role in software development, data analytics, or business intelligence.

Projects

  • CyberShield — my MCA capstone, a multi-modal cyber-threat detection platform combining four ML models (XGBoost + Random Forest for phishing URLs, TF-IDF + XGBoost for job-fraud text, an image-forensics pipeline with Grad-CAM, and Isolation Forest for anomaly detection) through a weighted risk-fusion engine. 96.4% accuracy / 0.993 AUC-ROC on phishing-URL detection. Graded A+.
  • HireSync — a full-stack (MERN) recruitment platform with role-based dashboards for recruiters and candidates, JWT auth, an analytics dashboard, and CI/CD with automated tests.
  • Toxicity Detection App — a Flask + PyTorch app using a fine-tuned BERT model to classify text across 6 toxicity categories, with batch analysis and a REST API. Built during my research internship at RVCE's Centre of Competence in Visual Computing.
  • Canteeno — a canteen management web app with full order-to-wallet functionality: employees browse a menu, place orders, and have the total deducted from their wallet automatically, with order history for both employees and admins.
  • SpendSense — a Flutter Progressive Web App for expense tracking and budgeting, installable and usable offline.
  • FocusSense — real-time, privacy-first study-attention analytics using MediaPipe/OpenCV and an optional CNN/LSTM classifier, with a live Flask + SQLite dashboard. MCA minor project, built with Sameer Patel.

Skills

Languages: Python, JavaScript, Java

Web & Mobile: React, Node.js/Express, MongoDB, SQL, Flutter

ML/Data: XGBoost, scikit-learn, PyTorch, TensorFlow, Power BI, Tableau

Tools: Docker, Git, CI/CD (GitHub Actions)

Contact

Pinned Loading

  1. CyberShield CyberShield Public

    CyberShield — multi-modal cyber deception detector: phishing URLs, fraudulent job posts & manipulated images, fused into one risk score. FastAPI/XGBoost backend, React frontend.

    Python

  2. FocusSense FocusSense Public

    FocusSense — real-time study-concentration detector using eye/head-pose tracking + a CNN+LSTM classifier. MCA minor project (with Sameer Patel).

    Python

  3. HireSync HireSync Public

    Full-stack (MERN) recruitment platform — role-based dashboards for recruiters and candidates, resume uploads, analytics, JWT auth, with CI/CD and automated tests.

    JavaScript

  4. SpendSense-flutter SpendSense-flutter Public

    Flutter PWA expense tracker — budgets, analytics & offline-first design with local browser storage

    Dart

  5. Toxicity-Detection Toxicity-Detection Public

    Flask + PyTorch app using a fine-tuned BERT model to classify text across 6 toxicity categories, with batch analysis, rephrase suggestions, and a REST API.

    HTML

  6. Canteeno Canteeno Public

    Canteen ordering system — employees browse a menu, order food, and pay from a wallet; admins manage the menu, employees, and view live order/revenue stats. React + localStorage, no backend.

    JavaScript