Advanced Recommender System Development

Domains: Machine Learning, Big Data, Cloud Computing
Project Overview: The project aims to develop and deploy an advanced recommender system for using state-of-the-art algorithms. It involves data gathering, algorithm selection and optimization, performance evaluation, and deployment on AWS with Hadoop and Spark integration. The goal is to improve user experience and increase sales by providing personalized product recommendations.

Roles: 1 full-time software development position (summer)
Stipend: Paid project
Project Duration: 2 months
Tasks/Deliverables:

• Data preparation, AWS environment setup, GitHub Actions configuration and database selection
• Implementation and comparison of various recommendation algorithms with detailed reports
• Fine-tuning selected algorithms to improve recommendation quality
• Deploy on Hadoop and Spark clusters on AWS servers for scalability
• Early testing and incorporation of feedback from the development environment
• Proper documentation of codebase and functionalities implemented

Submission Link: https://forms.gle/nMqj54pS7h6jojNA8

Deadline: 11:59 PM, 12th May, 2024

To enroll for the project, you must fill out the form above. For further credit, you can attempt and submit the assignment below to the best of your abilities, taking the aid of any tools online. We will contact you personally if you are shortlisted for the interview.

(Optional) Assignment: Create and compare movie recommendation systems

You are provided with a dataset for movie recommendation your task is to:
Task 1: Create a Recommendation system

• Parse movies.csv and create a content based recommendation system using TfidfVectorizer and cosine_similarity from sklearn
• Parse ratings.csv and create a collaborative filtering based recommendation system using Surprise or Librecommender 

Task 2: Prediction

• Generate 10 recommendations using: 
• content-based system using the user's historical movie preferences. 
• collaborative filtering system using user’s ratings 

Task 3: Evaluation

• Provide Metrics to judge recommendation systems 
• Compare and contrast the the two systems 

Resources:
Dataset - https://files.grouplens.org/datasets/movielens/ml-25m.zip
Surprise documentation - https://surprise.readthedocs.io/en/stable/index.html
Librecommender - https://pypi.org/project/LibRecommender/0.0.1/
 

For assignment queries, contact:

Email: satyamm435@gmail.com

Phone: 9324865787