Real-time Stream Analytics and User Scoring Using Apache Druid, Flink & Cassandra at Deep.BI

Hisham Itani
Mar 24 · 3 min read

Last October, we were honored to join the likes of Netflix, Alibaba, Salesforce, Airbus, Uber, Goldman Sachs, Yelp, Pinterest and many others presenting at Flink Forward in Berlin covering our area of expertise working with Apache Flink in combination with Apache Druid and Cassandra for real-time user and event scoring applications.

One of the hardest challenges we were able to tackle at Deep.BI is how to deliver customizable insights based on billions of data points in real-time, that fully scale from a single perspective up to millions of users.

At Deep.BI we track user habits, engagement, product and content performance — processing up to terabytes or billions of events of data daily. Our goal is to provide real-time insights based on custom metrics from a variety of self-created dimensions. The platform allows the performing of tasks from various domains such as adjusting websites using real-time analytics, running AI optimized marketing campaigns, providing a dynamic paywall based on user engagement and AI scoring, or detecting frauds based on data anomalies and adaptive patterns.

To accomplish this, our system collects every user interaction. We use Apache Flink for event enrichment, custom transformations, aggregations and serving machine learning models. The processed data is then indexed by Apache Druid for real-time analytics and Apache Cassandra for delivery of the scores. Historical data is also stored on Apache Hadoop for machine learning model building. Using the low-level DataStream API, custom Process Functions, and Broadcasted State, we have built an abstract feature engineering framework that provides re-usable templates for data transformations. This allowed us to easily define domain-specific features for analytics and machine learning, and migrate our batch data preprocessing pipeline from Python jobs deployed on Apache Spark to Flink, resulting in a significant performance boost.

This talk covers our challenges with building and maintaining our platform and lessons learned along the way, namely how to:

  • Evolve a continuous application processing an unbounded data stream,
  • Provide an API for defining, updating and reusing features for machine learning,
  • Handle late events and state TTL,
  • Serve machine learning models with the lowest latency possible,
  • Dynamically update the business logic at runtime without a need of redeploy, and
  • Automate the data pipeline deployment.

Challenges with Apache Druid, Flink or Cassandra? We can help.

You can find the full presentation here:

Speaker Information

Michał Ciesielczyk

Michał Ciesielczyk is the Head of AI Engineering at Deep.BI. He is responsible for researching, building and integrating machine learning tools with a variety of technologies including Scala, Python, Flink, Kafka, Spark, and Cassandra. Previously, he worked as an assistant professor at Poznan University of Technology, where he received a Ph.D. in computer science and was a member of a research team working on numerous scientific and R&D projects. He has published more than 15 refereed journal and conference papers in the areas of recommender systems and machine learning.

Sebastian Zontek

Sebastian Zontek is the CEO, CTO and co-founder of Deep.BI, Predictive Customer Data Platform with real-time user scoring. He is an experienced IT systems architect with particular emphasis on the production use of open source systems for big data such as Flink, Cassandra, Hadoop, Spark, Kafka, Druid in BDaaS solutions (Big Data as a Service), SaaS (Software as a Service), and PaaS (Platform as a Service). Previously, he was the CEO and main platform architect at Advertine. The Advertine network matched product ads with user preferences, predicting their purchasing intent using ML and NLP techniques.

Original post published by Hisham Itani on Deep.BI. Get in touch at ai@deep.bi!

Deep.BI

The next generation BI & AI platform

More From Medium

Also tagged Real Time Personalization

Also tagged Real Time Personalization

What if the machine is not learning but manipulating

66

Top on Medium

Ed Yong
Mar 25 · 22 min read

16.2K

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade