Build intelligent, real-time applications using Machine Learning
0 likes196 views
The document discusses the implementation of scalable, real-time machine learning at Hotstar using Apache Kafka to enhance user personalization for a large user base. It contrasts traditional model deployment methods with Kafka's capabilities for processing incoming data streams efficiently. This setup allows for real-time analytics and improved response times in generating recommendations.
Build intelligent, real-time applications using Machine Learning
- 1. Scalable, real-time Machine Learning using Apache Kafka
- 2. Agenda ● Traditional model deployment process ● 90 seconds to WoW ● Let’s process the incoming stream ● Demo ● What’s more? 2
- 3. $ whoami ● Personalisation lead at Hotstar ● Led Data Infrastructure team at Grofers and TinyOwl ● Kafka fanboy ● Usually rant on twitter @jayeshsidhwani 3
- 4. Machine Learning @ Hotstar ● ~150 mn users ● 4.8 mn peak concurrency ● 120K peak recommendation requests per second ● Diverse content in diverse languages 4
- 5. Traditional model deployment process 5 Model Training Data Lake Serialized Model Batch Predictions Recommendation APIs Offline Online ● One-day / few-hours batch pre-compute ● Slow time to react
- 6. Sense of urgency? 6 ● 90 seconds to convert a new user ● To power his experience, we need to know user’s gender, interests and more ● Need an always-thinking machine
- 7. Thinking streams 7 Data at Rest Data in motion ● Slow ● Batch-y ● Fast ● Sub-second
- 8. Enter Apache Kafka 8 ● Kafka is a scalable, fault-tolerant, distributed message queue ● Producers and Consumers ● Uses ○ Real-time applications such as: intelligent notifications, anomaly etc. ○ Asynchronous communication in event-driven architectures Diagram credits: http://kafka.apache.org
- 9. Real-time infrastructure at Hotstar 9 ● All clickstream data pushed into Apache Kafka ● Apache Kafka Streams to process events as they happen ● Incoming data available for everyone Intelligence Apple TV iOS ANDROID Roku STREAM PROCESSING FRAMEWORK Filter Window Join Anomaly Machine Learning
- 10. Demo Predict whether a flight is delayed in real-time 10
- 11. How to process a stream? 11 ML
- 12. Advanced use-cases 12 page-clicksProcessor nodes Source / Sink nodes video-plays predict-gender predict-interest 5-min trending videos Recommended for You Hotstar Streaming Platform