An end-to-end restaurant recommendation system built with Flask and Python. This project showcases a fully functional web application, hosted on Heroku, that helps users discover the best dining options based on their preferences.

Book Recommendation System- A Web app made using flask framework to recommend your favorite book using content based filtering and cosine similarity metrices.

Search engine for the Lex Fridman Podcast 🎤

Moodify is a Flask-based web application that seamlessly integrates facial emotion recognition (FER) with personalized music recommendations.

Resume Analyzer is a Flask and ML web application with Resume Analyze, Match, and Builder features. It scores and suggests resume improvements, matches resumes to job descriptions, and helps users create professional, structured resumes easily.

Determining similarity between two sentences in terms of semantic using pre trained Universal Sentence Encoder from TensorFlow.js

An Application to check plagiarism in Hindi

Recommend movies to users using Sentiment Analysis on Text data

A lightweight demo app which recommends similar jobs. Combines unsupervised ML + IR.

Design and compare the performances of Information Retrieval Models of TF-IDF, Cosine Similarity, BM25. Implemented query expansion using psuedo relevance feedback to display better results.

Developed an intelligent cologne recommendation platform that uses semantic search and natural language processing (NLP) to match users with fragrances. Users can describe their scent preferences in everyday language (e.g., “I’m looking for something sweet but masculine”).

The sample code repository leverages Azure Text Analytics to extract key phrases from the product description as additional product features. And perform text relationship analysis with TF-IDF vectorization and Cosine Similarity for product recommendation.

using feature maximisation for summarizing scientifc documents

Computes Pairwise Semantic Distance Between Tokens (ngrams, words, turns) in Ordered and Unordered Text

CraveCrafters is an AI-powered food ordering web application that seamlessly integrates a chatbot to assist users with menu browsing, order placement, and customer service. The system features a Node.js backend, a FastAPI-based chatbot, and an interactive frontend built with HTML, CSS, and JavaScript. It utilizes MongoDB as its database.

This project is a content-based movie recommendation web application that analyzes movie metadata (genre, cast, director, keywords) and provides accurate similarity-based movie recommendations. The system integrates with the TMDB API to fetch movie posters, trailers, and trending movies.

Portfolio Project.ipynb and Recommendation.py are the finalized Jupiter notebook scripts for this project. Other files are a work in progress to migrate into a web app.

This tool analyzes input text and suggests improvements based on semantic similarity to a list of standard phrases. It provides both a command-line interface (CLI) and a simple web-based user interface (UI).

📝 Exploratory analysis on Linkin Park lyrics