This project is a skincare recommendation system that uses webcam detection, image analysis, or manual input to identify skin concerns and suggest suitable products from a dataset.

DeepShelf is your AI-powered book buddy 📚🤖 — type what you’re in the mood for, and it finds the perfect novel using smart search + ranking ✨🔍

FRUDRERA is an AI-powered recipe recommender that suggests recipes based on the ingredients detected in a photo of your fridge. It utilizes object detection and OCR to identify ingredients and recommend recipes accordingly.

This project was done to fulfil the Machine Learning Terapan 2nd assignment submission on Dicoding. The domain used in this project is book recommendation.

SOEN471 Project - Team 10 - Winter 2024

An AI-based inventory optimization system that leverages machine learning to predict demand, recommend menu items, and streamline stock management for restaurants and food service businesses.. — all deployed through a real-time Stream lit web app.

Creating an Product Recommender System with Apriori and FPGrowth.

This is a collaborative filtering based books recommender system & a streamlit web application that can recommend various kinds of similar books based on an user interest.

All-in-one stealth OSINT reconnaissance tool for threat intel, bug bounty, and red teamers. metadata extraction, and parameter fuzzing included.

MovieMinds - Connect with similar cinephiles

A Multi-Agent Deep Reinforcement Learning (MARL) based system that recommends research papers based on user-selected categories. Multiple DQN-trained agents collaboratively learn optimal policies to suggest relevant and diverse papers tailored to user preferences.

A composition of Machine Learning Projects in python using algorithms in supervised, unsupervised, and deep learning.

Simple and interpretable recommender system using cosine similarity between movie vectors.

M.Sc. Courses in Data Science, including Machine Learning, Deep Learning, Statistics and Data Analysis, and Recommendation Systems.

Diet Recommendation System using KNN and built with Python for backend, ReactJS for frontend, and Docker for fast deployment.

Personalized smoking recommendations based on Collaborative Filtering.

Exploring Bloom embeddings as a compression technique for recommendation algorithms. Aimed at reducing the size of large input and output dimensionalities to enhance training and deployment efficiency on devices with limited hardware. This project evaluates Bloom embeddings using various hash functions and compares them with alternative methods.

Receive tailored suggestions for new reads based on your interests and books you have read before.

Provide book reccomendations using local LLMs, ensuring higher accuracy and reliability by cross referencing LLM with exisiting book database.

Project for HackSC (The University of Southern California Hackathon)