https://github.com/satya04m/recommender-system

The Recommender-System project is a machine learning-based application designed to predict user preferences and provide personalized recommendations. It leverages various algorithms, such as collaborative filtering and content-based filtering, to analyze user data and suggest relevant items. The project also includes a CI/CD pipeline for automating
https://github.com/satya04m/recommender-system

deep-learning deep-neural-networks mse neural-network python recommendation-system rmse-score

Last synced: 3 days ago
JSON representation

The Recommender-System project is a machine learning-based application designed to predict user preferences and provide personalized recommendations. It leverages various algorithms, such as collaborative filtering and content-based filtering, to analyze user data and suggest relevant items. The project also includes a CI/CD pipeline for automating

• Host: GitHub
• URL: https://github.com/satya04m/recommender-system
• Owner: satya04m
• Created: 2024-08-12T17:52:44.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-08-13T16:57:52.000Z (5 months ago)
• Last Synced: 2024-11-21T07:12:00.616Z (2 months ago)
• Topics: deep-learning, deep-neural-networks, mse, neural-network, python, recommendation-system, rmse-score
• Language: Python
• Homepage:
• Size: 1.51 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Recommender-System

## Overview

The **Recommender-System** project implements a robust recommendation engine for predicting user preferences. This project serves as a learning path for developing and deploying a recommender system using various data processing and machine learning techniques.

![System-Architecture](./System-Architecture.png)

## Tech Stack

- **Python**: Core programming language for implementing the recommendation algorithms.

- **Pandas**: Data manipulation and analysis library.

- **NumPy**: Supports large, multi-dimensional arrays and matrices.

- **SciKit-Learn**: Machine learning library for implementing algorithms.

- **Surprise**: A Python library for building and analyzing recommender systems.

- **Jupyter Notebook**: An open-source web application to create and share documents with live code, equations, visualizations, and narrative text.

- **Flask**: Micro web framework used to deploy the model as a web service.

- **Docker**: Containerizes the application for consistent deployment.

- **GitHub Actions**: Automates CI/CD pipeline for the project.

- **Kubernetes**: Orchestrates containerized application deployment.

## Output

Here are some examples of the outputs generated by the Recommender-System:

![Output Example 1](./OUTPUT1.png)

![Output Example 2](./OUTPUT2.png)

## Pipeline Flow

- **Data Collection**: Gathering and preprocessing data.

- **Model Training**: Using collaborative filtering, content-based filtering, or hybrid models.

- **Evaluation**: Evaluating the model’s performance using metrics like RMSE or precision.

- **Containerization**: Containerizing the application using Docker.

- **CI/CD Pipeline**: 

  - **Code Commit & Push**: Code is pushed to the GitHub repository.

  - **GitHub Actions Trigger**: GitHub Actions triggers the pipeline upon code push.

  - **Build & Test**: Builds the application and runs tests.

  - **Docker Build**: Builds a Docker image of the application.

  - **Push Docker Image**: Pushes the Docker image to a container registry.

  - **Deploy to Kubernetes**: Deploys the application to a Kubernetes cluster.

  - **Monitoring & Logging**: Set up Prometheus and Grafana for monitoring and logging the application’s performance.