Winning the On-Demand Economy with Spark and Predic9ve Analy9cs
Ankur Goyal, VP Engineering, MemSQL
Gartner BI March 20161
1 Deckset Plain Jane Black
We live in an on-demand economy
Consumers are condi.oned to instant services, like Uber, Stripe, and Airbnb
Where does that leave enterprises?
Racing to meet internal and external expecta1ons for speed and
personaliza,on
Batch processing is the enterprise enemy
Enterprises must move from overnight to
Real-&me, intra-day opera&ons
Because businesses need tomake every moment work for them
The key to harnessing data in real 1me?
A real-(me data pipeline with Apache Ka3a, Apache Spark, and an Opera(onal Database such as MemSQL
Massive Ingest and Concurrent Analy5cs• Instant accuracy to the latest repin
• Build real-5me analy5c applica5ons
• 1 GB/sec totaling 72 TB/day
Using Real-Time for Personaliza3on• Reach overlap and ad op/miza/on
• Over 60,000 queries per second
• Millisecond response /mes
MemSQL PowerStreamPredic'ng the global health of wind turbines
Dataset: 200,000 wind turbines, 20,000 wind farms
<$20,000 annual cost for AWS hardware
Let's build PowerStream
Move from a Real-Time Dashboard to Predic7ve Applica7ons
Ques%ons?Stop by MemSQL Booth #119