Case Study on how VistaPrint uses Amazon Personalize for product recommendations
Nothing mind-blowing, but a nice read if you have some time: A blog post by VistaPrint on how they use Amazon Personalize for creating personalized product recommendations.
Here is a summary of the blog post:
VistaPrint, part of Cimpress, serves millions of small businesses worldwide, offering marketing products and solutions for over two decades. The company has shifted to a cloud-native system for personalized product recommendations, utilizing Amazon Personalize, Twilio Segment, and other AWS services. This transition addressed previous challenges of scalability and efficiency in their recommendation system.
The new system aggregates data from various sources into a data warehouse, notably Snowflake, and uses Databricks for data transformation. Amazon Personalize then trains models with this data to predict user preferences and similar items. VistaPrint’s architecture also incorporates real-time data capture on their ecommerce site through Twilio Segment, allowing for instant recommendation updates as customers browse.
A personalization service, developed by VistaPrint, enhances the Amazon Personalize API with caching and integration capabilities. Moreover, a placement and offer engine enables data scientists and marketers to design tailored product placements, including in email marketing campaigns.
Since implementing this system, VistaPrint has seen a 10% increase in conversion rates and a 30% reduction in total cost of ownership. The solution exemplifies how cloud-native technologies and machine learning can enhance customer experience and operational efficiency.
Case study how simple recommendation techniques improve user experience in e-Commerce [Emilio Carrión @ MercadonaTech]
On YouTube’s recommendation system [Cristos Goodrow]
A look inside TikTok’s all-knowing algorithm [Charlotte Hu]
About The Author
Joeran Beel
I am the founder of Recommender-Systems.com and head of the Intelligent Systems Group (ISG) at the University of Siegen, Germany https://isg.beel.org. We conduct research in recommender-systems (RecSys), personalization and information retrieval (IR) as well as on automated machine learning (AutoML), meta-learning and algorithm selection. Domains we are particularly interested in include smart places, eHealth, manufacturing (industry 4.0), mobility, visual computing, and digital libraries. We founded or maintain, among others, LensKit-Auto, Darwin & Goliath, Mr. DLib, and Docear, each with thousand of users; we contributed to TensorFlow, JabRef and others; and we developed the first prototypes of automated recommender systems (AutoSurprise and Auto-CaseRec) and Federated Meta Learning (FMLearn Server and Client).