Ai+ Training

When building AI applications for real-time use cases, such as fraud prediction, predictive maintenance, prevention of customer churn and real-time recommendation engines, it is crucial to build your ML pipeline in a way that enables ingestion and analysis of real-time data on the fly, so that you can act upon this data in a matter of seconds to, for example, prevent fraud, or present an offer that will mitigate churn before it occurs.

In this presentation, we will review the challenges of handling real-time data in research and production environments and solutions that exists to enable you to build a real-time operational ML pipeline, that can handle events arriving in ultra-high velocity and high volume, calculate and trigger an action in seconds.

We will cover online and offline feature engineering and ML calculations in development and production, and how to monitor your real-time AI applications in production to detect and mitigate drift, using real customer case studies.