tf-idf-vectorization

✨ This is my university unit assignment on AI Algorithms. A movies recommendation website using TF-IDF and Cosine Simillarity.

Retrieve Information from Text Documents with TF-IDF model and dimention reduction with (Latent Semantic Indexing)LSI.

Full-featured information retrieval system that indexes and enables searching through the CACM (Communications of the ACM) corpus.

Understanding human emotions in text is crucial for many applications such as customer feedback analysis

I developed a sophisticated ML model using LLMs to predict user preferences in chatbot interactions.implemented a comprehensive data preprocessing pipeline,including feature extraction and encoding,to optimize performance. conducted extensive hyperparameter tuning and evaluation, enhancing accuracy and in AI-driven conversational systems.

Interactive NLP-based AI system designed to manage cinema bookings and provide a seamless user experience.

Recommendation Engine for SHL assessment product catalog based on user's job role, skills, etc.

AniVerse: A comprehensive anime recommendation platform with a React/Next.js frontend, Node.js backend for user management, and a Python/Flask API for personalized recommendations.

Plagiarism detector made by using NLP and TF-IDF which is able to differentiate between original and coied/plagiarised.

Content-based movie recommender with FastAPI backend + TF-IDF similarity + Dockerized ml website

A hybrid Steam game recommendation engine combining Content-Based Filtering, Collaborative Filtering, and MMR re-ranking for diverse, personalized suggestions.

Email Spam Detector - Machine Learning Model (Dockerized) that classifies messages as spam or not spam using a trained Naive Bayes model. The model is built using scikit-learn and is packaged inside a Docker container for easy deployment and usage.

Build a Web App called AI-Powered Recipe Recommender App

This repository contains an advanced, NLP-powered algorithm designed to match human to human pair based on their ovarall life experience. Instead of relying on rigid, rule-based text matching, this system uses a Weighted Matrix Algorithm included TF-IDF & Cosine Similarity, Min-Max Normalization , semantic matching to match the most accurate pair.

System to recommend movies based on user-inputted movie

An end-to-end review analysis pipeline that processes 21,000+ real Amazon reviews using both traditional machine learning (TF-IDF + Logistic Regression) and modern AI (Google Gemini zero-shot classification, aspect extraction, and topic modeling) -wrapped in an interactive Streamlit dashboard. Built with Python, scikit-learn, Streamlit, and Gemini

Tool for processing, categorizing, and searching through PDF documents and images using machine learning and OCR.

CADL Activites of NLP (PMC2421A).

Flipkart product recommendation system using TF-IDF and Cosine Similarity for content-based filtering. Built with Python & Streamlit, it delivers smart, explainable product suggestions with interactive analytics, discount insights, and CSV export — all through a clean, responsive UI.