A Data Science Central Community
The company partnered with Dataiku to develop a machine learning solution that validates new customer data against over 1 billion emails and events. The result is an automated system that saves time and money for SendinBlue while maintaining the integrity of their platform, a crucial cornerstone of their business.
SendinBlue is one of the leading relationship marketing companies in the world and works with over 50,000 companies across the globe, delivering more than 30 million emails and text messages each day. To ensure their customers' emails reach the inbox and that SendinBlue's delivery system maintains the highest reputation, the company created a machine learning platform with Dataiku to automatically validate new customer applications using historical data coming from over 1 billion emails and associated events. The resulting system saves time and money for SendinBlue by automating checks that filter out potential spammers before they are allowed access to the SendinBlue platform.
SendinBlue previously relied on manual validation of new customers, checking (among other things) the quality of their databases, but it was a painful and long process that required a large workforce. It also severely delayed account validation for customers and was therefore detrimental to SendinBlue’s reputation. Faced with a growing customer base, SendinBlue could not continue down the path of manual validation and feasibly scale.
To move away from manual validation and allow for rapid growth, SendinBlue turned to Dataiku Data Science Studio (DSS), leveraging their expertise in the area of automated fraud detection. With Dataiku, SendinBlue built a scalable solution using historical data coming from more than 1 billion emails and associated events (clicks, opening rates, bounces, etc.), thousands of blocked accounts, and hundreds of fraud criteria (IP addresses, history, behaviours, etc.).
SendinBlue’s new process allows them to:
Analyse new customers and automatically classify them as “good,” “bad,” or “uncertain.”
Once the new customers are classified, an algorithm determines the customer’s credibility by taking into account sending volume, the scoring of the contacts, etc.
Depending on the customer’s risk score, they may be blocked, validated, or sent to customer care for manual analysis.
The resulting solution allows SendinBlue to scale by serving customers more quickly. This analytics initiative saved the equivalent of a full time job and rationalized the global validation process, letting SendinBlue exponentially scale its team and customer growth. On top of this, SendinBlue is able to provide a better customer experience by considerably shortening validation delays. Initially handling just 24 percent of the new accounts as part of a staged rollout, the machine learning model now handles most of the new accounts.
Dataiku also ultimately allowed SendinBlue to be more accurate in their validation, thereby increasing their email reputation; the first iteration of their model leverages Random Forest and has an 83 percent precision rate on email address classification.
“Dataiku helped us to massively scale our team’s productivity while delivering a better user experience,” said Armand Thiberge, CEO of SendinBlue. “We are now going to leverage the power of machine learning to aid our customers in real time while they use SendinBlue. As the fraudsters’ systems always evolve, we’ll soon leverage a new generation of advanced algorithms to detect new kinds of fraud.”
Dataiku DSS is an advanced analytics software solution that enables companies to build and deliver their own data products more efficiently. Thanks to a collaborative and team-based user interface for data scientists and beginner analysts, to a unified framework for both development and deployment of data projects, and to immediate access to all the features and tools required to design data products from scratch, customers such as L’Oreal, Intermedix, Hostelworld, and many more easily apply machine learning and data science techniques to all types, sizes, and formats of raw data to build and deploy predictive data flows.
To learn more about what Dataiku can do visit: www.dataiku.com
SendinBlue is an intuitive SaaS solution empowering B2B and B2C businesses, e-commerce sellers and agencies to build customer relationships through digital marketing campaigns, transactional messaging, and marketing automation. Founded in 2012, SendinBlue is a venture-backed startup dedicated to making the most effective marketing channels accessible to all businesses. Compared to other marketing solutions built for enterprise-level budgets and expertise, SendinBlue tailors its all-in-one suite to suit the marketing needs of growing SMBs. Headquartered in Paris with expanding offices in Seattle and Noida, India, SendinBlue has supported more than 600,000 users across 140 countries.
Dataiku develops Dataiku Data Science Studio, the unique advanced analytics software solution that enables companies to build and deliver their own data products more efficiently. Thanks to a collaborative and team-based user interface for data scientists and beginner analysts, to a unified framework for both development and deployment of data projects, and to immediate access to all the features and tools required to design data products from scratch, users can easily apply machine learning and data science techniques to all types, sizes, and formats of raw data to build and deploy predictive data flows.
Hundreds of customers in industries ranging from e-commerce, to industrial factories, to finance, to insurance, to healthcare, and pharmaceuticals use DSS on a daily basis to collaboratively build predictive dataflows to detect fraud, reduce churn, optimize internal logistics, predict future maintenance issues, and more. Dataiku has offices in Paris and New York. Dataiku raised a $21 million pound Series B round earlier this month, led by Battery Ventures. Learn more at: www.dataiku.com