Dr. Jamie Allsop auf der MLcon

Machine Learning: Algorithmische Architekturen, Echtzeit-KIs und die Suche nach dem Alpha
Keine Kommentare

Ein KI-System zu bauen ist schwer. Echtzeit-KIs bringen aber nochmals ganz eigene Herausforderungen mit sich. Dr. Jamie Allsop berichtet in diesem Video von der Machine Learning Conference 2017, wie algorithmische Architekturen dabei helfen, KI-Systeme mit Echtzeit-Funktionalität zu bauen.

Jamie Allsop stellt in seinem Talk ein KI-System vor, das mit Hunderten von Wertpapieren gleichzeitig handeln kann. Dazu werden relevante Signale in Echtzeit aus Social-Media Feeds extrahiert und ausgewertet. Der Vortrag befasst sich mit algorithmischen Architekturen und der Herausforderung, die Beziehungen zwischen den Branchen und Sektoren zu korrelieren.

English Abstract:

Building any AI system is hard but building a real-time AI brings its own challenges. At Yedup and Clearpool we have been building a real-time AI system to trade against hundreds of securities simultaneously by extracting fundamental signals from real-time social media feeds. We’ve gone back to first principals to build out a technology stack from scratch to meet our specific needs.

This talk looks at how we’ve exploited algorithmic architecture to build a real-time AI system that delivers market leading alpha. That’s interesting in itself, but what’s more interesting is looking at some of the challenges that we’ve had to overcome in order to deliver a system that can not only trade hundreds of instruments simultaneously, but that can also correlate the relationships across industries and sectors to extract yet more alpha.

These are challenges that would be applicable to any similar class of problems (such as real-time AI) and this talk explores a couple of the key ones, such as maintaining and recovering with huge amounts of in-flight state to deliver fast, scalable and robust AI systems.

Der Speaker: Dr. Jamie Allsop

Currently Head of Technology at TP ICAP and Director of clearpool.io Jamie is leading the development of a next generation exchange platform targeting MiFID II and emerging economies. Previously at the NYSE he was responsible for their market data platform and next generation projects. Impacted by the Flash Crash in 2010 he acted as a technical witness to the SEC. A member of the BSI C++ ISO Standards Panel and previous co-author of a best seller on C++ he enjoys getting his hands dirty in code. Creator of cuppa, a python Scons-based build framework to simplify building complex C++ systems. Passionate about agile development, and a long time speaker on the topic, he particularly enjoys helping distributed teams embrace agility.

Unsere Redaktion empfiehlt:

Relevante Beiträge

Hinterlasse einen Kommentar

Hinterlasse den ersten Kommentar!

avatar
400
  Subscribe  
Benachrichtige mich zu:
X
- Gib Deinen Standort ein -
- or -