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

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

In this notebook we analyze and classify news articles using machine learning techniques, including Logistic Regression, Naive Bayes, Support Vector Machines, and Random Forests. Explore text vectorization and NLP for accurate news categorization.

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.

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

Build a Web App called AI-Powered Recipe Recommender App

System to recommend movies based on user-inputted movie

AniVerse is an anime recommender system which recommends user based on explicit feedback from user.

Market trends and investment insights

This Spam Detection model classifies emails as spam or not using TF-IDF and Logistic Regression. It includes evaluation metrics and sample tests. The repository provides the complete code and dataset for easy use and modification.

"This repository consists of **Acne Detection using YOLO** for identifying acne from facial images and **Machine Learning-based Product Recommendation** for suggesting suitable skincare products based on acne severity and skin type."

Predicting the topic of news articles

The purpose of this project is to build a machine learning model to classify SMS messages as either "spam" or "ham" (not spam). Using TF-IDF vectorization and LinearSVC, it reads an SMS dataset, transforms text data into numerical features, and trains a model to distinguish between spam and ham. The "SMSSpamCollection" dataset has labeled messages.

Repository for the course Essentials in Text and Speech Processing Fall 2024

Spam Email Detector

The Fake News Detection system features a user-friendly Tkinter-based GUI that allows users to input a news article, title, and author. Users can select from six machine learning models to instantly classify the news as Real or Fake. The interface provides quick and interactive predictions, making it ideal for real-time demonstrations.

Prediction of airline passenger referrals using Logistic Regression, GridSearchCV, and TF-IDF vectorization with Python, Pandas, Scikit-learn, and Excel.

Built an end-to-end text classification model using TF-IDF vectorization and models like Logistic Regression and SVM. Includes exploratory data analysis, model evaluation

Amazon product review sentiment analysis using Logistic Regression (LR), Support Vector Machine (SVM), and Naive Bayes (NB) multiclass as classifier models, Synthetic Minority Oversampling Technique (SMOTE) as feature oversampler, and TF-IDF vectorization as feature, Synthetic Minority Oversampling Technique (SMOTE) as oversampler, and k-fold CV.