Apollo builds a scalable, robust, hyper-personalized consumer insights platform with Quantiphi using AWS services

Apollo Program helps businesses personalize their customer messaging with an AI-based hyper-personalized marketing platform developed on Amazon Web Services (AWS). Through the marketing platform, businesses can ideate, plan, and execute integrated marketing campaigns to attract and convert high-quality leads, improve brand perception, and build deeper customer loyalty.

Apollo Program had the vision to create an AI-based consumer behavior analysis platform for hyper-personalized marketing to help marketers tailor content based on individual preferences and achieve true hyper-personalization. To achieve this vision, Apollo Program chose to partner with Quantiphi. Through Quantiphi's platform, Apollo Program can extract multi-level deep marketing insights to help its customers. The solution enables Apollo Program to detect existing and future problems and design effective strategies to increase customers' digital user base. The platform is exclusively designed for the Apollo Program, and only its proprietary tools can be integrated.

Quantiphi is an AWS Partner with competencies in Applied AI, MLOps, Data & Analytics, and Data Migration. These competencies further substantiate Quantiphi’s ability to build and deploy AWS solutions at scale, leverage AI/ML, and develop critical solutions to address business challenges. Quantiphi’s work over the years with Apollo only cemented Apollo's faith to continue to engage with Quantiphi.

Quantiphi’s solution captures data about the websites visited by a customer and classifies them into a broad category based on keywords contained in the web page to better understand the web page’s offerings and value. Based on the strong correlation between a web page’s offerings and a customer’s fundamental interests, a marketer would be better placed to make critical marketing strategy decisions for running campaigns and creating content. 

To realize Apollo’s vision of achieving hyper-personalization, Quantiphi leveraged the AWS cloud platform and broke down the vision statement into the following technological components.

Cost-effective and fully managed ETL pipeline

• Quantiphi used services such as Amazon Glue, Amazon Athena, AWS Lambda, AWS CodePipeline for scheduling a daily batch process and used Amazon Cloudwatch alarms and SNS alerts for data governance.
• The company achieved a 60% reduction in monthly costs by implementing lifecycle policies on intermediate and raw tables, purchasing reserved instances for existing infrastructure, and identifying and stopping non-active instances.

Creating a feature-rich consumer data platform for both internal and external use

• Quantiphi developed a self-service consumer data platform which automates tasks such as the creation of consumer pools with multiple combinations of first party and third-party metrics and the creation of customer assets such as accounts, brands, projects, and Pixels.
• Quantiphi developed a reporting feature in the web app that provides automated consumer behavior insights and visualizations.
• Using NLP, Quantiphi derived keywords, named-entities, language, and sentiment from the web-scraped data.
  

Revising the existing pixel server to make it more scalable, robust, and secure

• Quantiphi proposed a revised solution architecture for Pixel Server, which reduced the Pixel fire response time to microseconds. Downtime and risk was reduced by implementing the blue-green deployment technique to move Pixel traffic to new infrastructure.
• Pixel Server can now integrate multiple data partners, handle user opt-out requests, and scale to international geographies.
  

With AWS cloud services, Quantiphi and Apollo Program were able to build a scalable, robust, hyper-personalized consumer insights platform that allows marketers to:

• Attract and convert high-quality leads and Improve brand perception
• Build deeper customer loyalty by interacting directly with the end consumer
• Achieve automation of Apollo’s ETL pipeline using AWS services like Amazon Athena and Amazon Glue to process 45 Terabytes of data per month
• Achieve complete automation of data pull requests to fasten the delivery time by 88%, and achieve more than 95% accuracy in results.
• Ability to leverage additional survey data sources along with the data received from the data partners for Apollo’s data-centric business partners