Hi, I'm Mayank Bansal

I build

Specialized in AI, Machine Learning, and Python Development

View My Work Contact Me

About Me

Mayank Bansal

Who am I?

I'm a BTech CSE student with hands-on experience in Python development, machine learning, and web APIs. I've built and deployed multiple end-to-end ML projects involving real-world data, model deployment, and frontend-backend integration.

I'm passionate about solving real problems through intelligent systems and always looking for opportunities to apply AI/ML to create meaningful solutions.

Education

BTech in Computer Science & Engineering

Lovely Professional University — 2nd Year

Download CV View CV

My Certificates

Certificate 1
× Zoomed Certificate

My Skills

Programming Languages

Python
C++
JavaScript
HTML/CSS
Java

Machine Learning

Retrieval Augmented Generation (RAG)
Scikit-learn
Pandas & NumPy
Matplotlib
TF-IDF
TensorFlow
PyTorch
FAISS
Sentence Transformers
Gemini API
Model Fine Tuning
ResNet50

Web Development

Flask
REST APIs
UI Design
Deployment

Tools

Git & GitHub
Jupyter Notebook

My Projects

PDF Question Answering System

PDF Question Answering System (RAG)

A Retrieval-Augmented Generation system that answers questions from PDF documents. Uses Sentence Transformers for embeddings, FAISS for similarity search, and Gemini API with guardrails to prevent hallucinations.

Python Flask FAISS Sentence Transformers Gemini HTML CSS JavaScript
GitHub
Computer Vision Image Search

Visual Search Engine

End-to-end image search system using ResNet50 for feature extraction and FAISS for efficient similarity retrieval. Users upload images to find visually similar results from a dataset in real-time.

Python PyTorch ResNet50 FAISS Flask HTML/CSS/JS
GitHub
AI Complaint Triage & Routing System

AI Complaint Triage & Routing System

End-to-end ML system for structured complaint handling using TF-IDF and Logistic Regression to classify departments and urgency. Features hybrid credibility scoring, auto-generated follow-up questions, database storage, and admin dashboard for oversight.

Python TF-IDF Scikit-learn Flask Database HTML/CSS/JS
GitHub
WasteSnap - Smart Waste Classification

WasteSnap – Smart Waste Classification

A real-time waste classification web application that identifies 9 types of waste using a custom-trained MobileNetV2 model. Features include real-time classification, confidence scores, and disposal tips.

Python TensorFlow Flask MobileNetV2 HTML/CSS/JS
Live Demo GitHub
Mood2Mail Project

Mood2Mail – Email Tone Analyzer

Built a tone-detection app using TF-IDF with Naive Bayes. Real-time feedback on email tones (Friendly, Formal, Aggressive, etc.) via Flask API and JS frontend.

Python TF-IDF Flask JavaScript
Live Demo GitHub
Dyslexia AI Assistant

Dyslexia AI Assistant

An AI-powered web application designed to make reading easier for individuals with dyslexia and other reading difficulties. It uses a fine-tuned T5 transformer model to simplify complex text, making it clearer and more readable without losing meaning.

Python Flask T5 Transformer HTML/CSS JavaScript
GitHub
DigiDetect Project

DigiDetect – Handwritten Digit Recognition

A full-stack web app that recognizes handwritten digits with high accuracy. Users can draw a digit on a canvas or upload an image, and the app instantly predicts the digit and shows the model's confidence.

Python TensorFlow Flask HTML/CSS/JS CNN
GitHub
Real Time ASL Hand Signs Predictor

Real Time ASL Hand Signs Predictor

Built a sign language translator using a CNN trained on the ASL dataset. Preprocessed data with GPU acceleration in Google Colab and integrated the model with OpenCV and MediaPipe for real-time hand sign detection. A strong prototype toward bridging communication gaps.

Python TensorFlow/Keras CNN OpenCV MediaPipe
GitHub
BiasX-Ray Project

BiasX-Ray – Real-Time Bias Detector

A web-based tool that detects bias in team chat messages in real-time. Identifies gender-coded words, microaggressions, and offers inclusive rewrites to foster respectful communication.

Python Flask NLP (spaCy, NLTK) JavaScript
Live Demo GitHub
StyleNet Project

StyleNet – Fashion Image Classifier

A fashion image classifier powered by a CNN trained on Fashion MNIST. Achieved ~91% accuracy, deployed with Flask, and features a clean frontend for easy testing and image uploads.

Python TensorFlow Flask HTML/CSS/JS CNN
GitHub
Music Genre Classification

Music Genre Classification

Used Librosa to extract audio features and predict genres via Flask API. Handled MP3/WAV input formats and resolved backend deployment issues (CORS, NumPy compatibility).

Python Librosa Flask API Audio Processing
GitHub
Fake Job Posting Detector

Fake Job Posting Detector

Developed a Logistic Regression model to detect fraudulent job listings. Deployed with a clean, responsive frontend using Flask and vanilla JS.

Python Scikit-learn Flask JavaScript
Live Demo GitHub
Car Mileage Predictor

Car Mileage Predictor

Trained a Linear Regression model with feature engineering and Grid Search. Built a deployment-ready interface to predict mileage from user inputs.

Python Linear Regression Grid Search Flask
Live Demo GitHub
Movie Recommendation System

Movie Recommendation System

Created a content-based recommender system in Python. Suggests similar movies based on title and genre correlations.

Python Content-based Filtering Data Analysis
GitHub

Blogs & Research Papers

Sharing my thoughts and insights on AI, technology, and more. Check out my latest articles below.

AI in Fiction and in Reality
April 27, 2025

AI in Fiction and in Reality

Exploring how science fiction shapes our understanding of AI and comparing it with the reality of current AI technology. An analysis of misconceptions and the true nature of modern AI applications.

Blog AI Science Fiction Technology
Read More Original Post
Google Veo 3 and the Death of Reality
May 29, 2025

Google Veo 3 and the Death of Reality

An in-depth analysis of Google's Veo 3 AI video generation model and its implications for creativity, reality, and the future of content creation.

Blog AI Video Generation Technology
Read More Original Post
Mood2Mail Research Paper
July 18, 2025

Mood2Mail: Real-Time Email Tone Analyzer (Preprint)

Preprint describing Mood2Mail, a lightweight real-time email tone analyzer using TF-IDF with Logistic Regression and Naive Bayes. Includes methodology, dataset details, and results.

Research Paper ML NLP
Read Paper Repo
Coming Soon

More Articles Coming Soon

Stay tuned for more articles on artificial intelligence, machine learning, and their applications in solving real-world problems.

Get In Touch

Email

bansalmayank1414@gmail.com

Phone

+91 8708574164