[GIW-MII-UGR-2016-2017] Desarrollo de un Sistema de Recomendación basado en Filtrado Colaborativo "User Based" desde cero y con Mahout Taste

Java and Spring demo API for the Oatfin platform.

A recommender engine similar to those used by Netflix or Amazon.

some examples via spark,hadoop

User-Based Collaborative-Filtering recommendation engine built with Java

ML Recommendation System Skeleton / Product Comparison Service (Java 11 / MongoDB / Spring)

recommend

This project is proof-of-concept work of developing Mahout Recommendation Engine. The technology used is Spring Boot framework and MongoDB as the database.

A sample of my work from APCS (AP Computer Science) at Homestead High School.

A DIY version of a simple movie recommendation system.

In this project we build docker deployable adaptive recommendation engine for meals to maintain users’ nutritional intake and variety in upcoming meals using Flask. We encode preparation steps of recipes in vector space to find similarities between recipes using math formula. We develop interactive Android App for users to log daily meals.

Algorithm for recommend food based associations rule

a Java-based recommendation engine using t-SNE techique and QuadTree algorithms

A media recommendation web app.

Java and Spring demo api for the Oatfin platform

Maidenpool SDK for the Java programming language.

Apache Spark Recommendation/Machine Learning Api Service

Spring Boot Starter for using Mahout as a recommendation engine for item-based collaborative filtering.

Generic Recommendation Engine Skeleton

A Java implementation of Alternating Least Squares (ALS).