**** PRE-REGISTER HERE: https://forms.gle/dVrCfUrxnjuozxDEA
Please complete this simple form to expedite the sign-in process.

**** IMPORTANT: please bring a photo ID to check in at security on the day of the event

PLEASE JOIN US @ FINRA as our meetup crosses the border to MD for the first time!

Title: ML at Scale using Apache Spark. Develop, Interpret and Monitor.

Abstract

Join us for a 360 view of Machine Learning at scale, covering model development, results interpretation and results monitoring technique. In this talk Ahmed Ibrahim will walk through step-by-step approaches on how to apply Spark MLib, Lime and Drift Measurements. This talk is intended to give you a 360 view on how to apply machine learning at scale from a project perspective.

During this session we will write Scala code using Spark and MLIB Random Forest Classifiers to create your first ML model that runs against big data. If you don't know Scala or these frameworks, don't worry -- the examples are easy to follow, and you'll come away better prepared to do the same thing with the language and frameworks of your choice.

Takeaways from the session:

(a) code on GitHub having sample code in Scala implementing MLIB classifiers

(b) code on GitHub that runs at scale within a Jupyter or DataBricks.

About the Presenter

Ahmed Ibrahim, a Principal Architect at FINRA in assurance engineering, will lead a discussion on Machine Learning on AWS. In his role, Ahmed is responsible for the architecture of assurance processes for market surveillance projects. His work relates to big data analytics and machine learning based market manipulation detection. In his previous work, Ahmed architected solutions for enterprise systems for multiple international trade facilitation systems and national security systems. His interests include graph analysis and visual intelligence led investigation techniques. Ahmed received a B.Sc. in Electrical Computer Engineering in 2001.

PARKING

FREE and readily available