A Recommender System is a powerful tool for predicting user preferences and guiding decision-making in various industries. The Specialization offered by University of Minnesota covers fundamental techniques in recommender systems, from non-personalized and project-association recommenders to advanced methods like matrix factorization and hybrid machine learning techniques. Throughout the course, you will master the art of building recommendation systems, implementing collaborative filtering, and using spreadsheet-based tools for analysis.
Designed for both data mining experts and data literate marketing professionals, this Specialization combines interactive exercises and real-world case studies to provide a well-rounded learning experience. By the end of the program, you will be equipped to implement and evaluate recommender systems, culminating in a Capstone Project that integrates the course material into a realistic recommender design and analysis project.
Certificate Available ✔
Get Started / More Info
The course modules provide a comprehensive understanding of recommender systems, covering non-personalized and content-based recommendations, collaborative filtering, evaluation metrics, matrix factorization, and a Capstone Project.
This course introduces the concept of recommender systems, including non-personalized and content-based recommendations. You will learn to compute recommendations using basic spreadsheet tools and gain familiarity with the open source LensKit recommender toolkit through the honors track.
Explore fundamental techniques for making personalized recommendations through nearest-neighbor techniques. Learn user-user and item-item collaborative filtering algorithms, including variations and their benefits and drawbacks. Implement and evaluate these techniques to understand their practical implications.
Gain familiarity with various evaluation metrics for recommender systems, including prediction accuracy, rank accuracy, decision-support, diversity, and product coverage. Learn how to rigorously conduct offline and online evaluations to compare different recommender system alternatives for diverse applications.
Learn a variety of matrix factorization and hybrid machine learning techniques for recommender systems. Understand the practical details of building recommender systems based on reducing the dimensionality of the user-product preference space. Explore techniques that combine the strengths of different algorithms into powerful hybrid recommenders.
This capstone project course brings together everything you've learned about recommender systems algorithms and evaluation into a comprehensive recommender analysis and design project. Select and justify the design of a recommender system through analysis of recommender goals and algorithm performance.
Deploying a PyTorch Computer Vision Model API to Heroku offers hands-on experience in deploying a Flask REST API using a pre-trained PyTorch image classification...
Learners will acquire the essential skills for extracting, cleaning, and preparing diverse data sources for NLP processes in this course.
Simple Linear Regression for the Absolute Beginner is a practical, hands-on guided project to understand, build, and apply simple linear regression models using...
Build a customer chatbot using Vertex AI in this 1-hour project-based course.