Download PDF
Provectus > Case Studies > IMVU's Transformation: Leveraging AWS for Advanced Analytics and Machine Learning
Provectus Logo

IMVU's Transformation: Leveraging AWS for Advanced Analytics and Machine Learning

Technology Category
  • Analytics & Modeling - Machine Learning
  • Platform as a Service (PaaS) - Application Development Platforms
Applicable Industries
  • Cement
  • Construction & Infrastructure
Applicable Functions
  • Logistics & Transportation
  • Product Research & Development
Use Cases
  • Behavior & Emotion Tracking
  • Livestock Monitoring
Services
  • Cloud Planning, Design & Implementation Services
  • Data Science Services
The Challenge

IMVU, the world’s largest avatar-based social network, was facing challenges with its aging on-premise data platform. The company wanted to enhance and re-architect their platform to support advanced analytics and Machine Learning use cases. However, with an exponentially growing data volume and a monolithic Hadoop architecture, the IMVU team was struggling to efficiently utilize user-generated data. The existing infrastructure limited innovation and capacity for advanced analytics. IMVU’s analysts lacked the tools to rapidly generate business-critical reports on customer in-game behavior at scale. They were working with historical data in batches, which resulted in late reports, inaccurate assumptions about customer in-game purchases, slower sales, and loss of profit. The analytics team also lacked a test environment to efficiently check analytics assumptions. The platform was powered by a 90-node on-premise Hadoop cluster, which was not cost-efficient and resulted in high costs and low efficiency.

About The Customer

IMVU is the world’s largest avatar-based social network with over 7 million monthly users. The platform allows users to customize their avatars, chat with friends, shop, hang out at cool parties, and earn real money by creating virtual products. IMVU was one of the pioneers and early adopters of Apache Hadoop, taking advantage of Big Data technologies before they became mainstream. Despite maintaining deep internal expertise, the company was facing challenges in supporting and upgrading their 90-node Hadoop cluster and in-house built tooling. The company sought to modernize their platform’s data architecture by introducing CI/CD, Infrastructure as Code (IaC), and other best practices.

The Solution

IMVU partnered with Provectus and AWS to re-architect their data platform for the AWS cloud. The company migrated Apache Hadoop clusters to Amazon EMR, optimized Hive/Spark jobs, and mirrored Apache Kafka data streams to the cloud. The data pipelines were modernized to meet the requirements for a modern Data Platform using open source solutions and AWS services. The platform was designed to use Airflow for job scheduling and monitoring, running on Amazon EKS. Data pipelines were optimized to utilize Amazon’s EMR Autoscaling policies, to account for increasing data volumes without sacrificing time of delivery for reports. The Business Intelligence (BI) layer was optimized to serve the needs of IMVU’s data analytics team. Provectus deployed and built a custom solution using PrestoSQL for data access and Apache Ranger for managing the security aspects of the Data Platform.

Operational Impact
  • The re-architected data platform provided IMVU with a scalable, cloud-native infrastructure. This modernized platform enabled IMVU to generate insights into customer lifetime behavior and improve customer retention with Machine Learning. The team can now take advantage of vast amounts of data generated by users to generate comprehensive reports on in-game purchases, customer engagement, and avatar preferences. The analysts can generate reports much faster, whenever they need to. The company has overcome significant technological barriers to fast and seamless code deployments. The re-architected platform has created a solid foundation for their cloud-based products and introduced the potential for using Artificial Intelligence and Machine Learning for customer retention. The company managed to grow by no less than 50% while reducing operational expenses during the Covid-19 pandemic.

Quantitative Benefit
  • 400 Spark Jobs

  • 2x TCO Optimization

  • 1PB Processed Daily

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.