Building a PAI-based Recommender System within 10 Minutes

Are you an AI enthusiast with a keen eye on innovation? Sign up for the Alibaba Cloud Global AI Innovation Challenge and win big! Sign Up Here >>

By GarvinLi

In this article, Alibaba technical expert Aohai introduces how to establish a simple recommender system based on Machine Learning Platform for AI (PAI) within 10 minutes. This article focuses on four parts: the personalized recommendation process, collaborative filtering algorithm, architecture of the recommender system, and practices.

1) Personalized Recommendation Process

2) Collaborative Filtering

3) Architecture of the Recommender System

4) Practices

Next, we create the two tables in Tablestore in the required format.

Then, we use DataWorks to migrate the data of the two tables from PAI-Studio to Tablestore.

Then, in PAI-AutoLearning, we can configure a policy for the two tables in Tablestore.

Finally, we convert this policy to a PAI-EAS service. You can check how to call this service here. The result obtained by the user is this service.

To update and iterate all the data involved, you can modify the original table. The whole set of services can be automated. Therefore, you can use the DataWorks data scheduling system to make an automated system. Then, you only need to update the raw data on a daily basis, and all the remaining services can be automatically completed.

Learn more about Alibaba Cloud Machine Learning Platform for AI (PAI) at

The views expressed herein are for reference only and don’t necessarily represent the official views of Alibaba Cloud.

Original Source:

Gain Access to Expert View — Subscribe to DDI Intel

Follow me to keep abreast with the latest technology news, industry insights, and developer trends.