More companies are using big data to gain insights into their business as it becomes more mainstream. This has led to a surge in what the industry calls, “fast data” – data that’s continuously arriving and processed as it arrives. As a result, the number of open source projects for processing fast data has exploded in recent years.
In this webinar, Tim Renner, Ph.D., will walk through three key technologies for processing streaming data by working through an example: computing online advertising click-through rates (the number of clicks per view) in real-time at scale. Tim will cover the microbatch sequence-based approach used by Apache Spark, the continuous event-based approach used by Apache Storm, and will discuss the architectural considerations of streaming data systems by showing how apache Kafka fits into the picture.
- Clickthroughs and real-time processing
- Windowing and Apache Spark
- Continuous event processing and Apache Storm
- Architecture and design with Apache Kafka
- Final Q&A | Next Steps to Get Started