Managing the Complexity of Processing Financial Data at Scale - An Experience Report

Abstract

Financial markets are extremely data-driven and regulated. Participants rely on notifications about significant events and background information that meet their requirements regarding timeliness, accuracy, and completeness. As one of Europes leading providers of financial data and regulatory solutions vwd processes a daily average of 18 billion notifications from 500+ data sources for 30 million symbols. Our large-scale geo-distributed systems handle daily peak rates of 1+ million notifications/sec. In this paper we give practical insights about the different types of complexity we face regarding the data we process, the systems we operate, and the regulatory constraints we must comply with. We describe the volume, variety, velocity, and veracity of the data we process, the infrastructure we operate, and the architecture we apply. We illustrate the load patterns created by trading and how the markets' attention to the Brexit vote and similar events stressed our systems.

Panda

“…For instance, this year's DEBS Grand challenge requires triggering pattern detection queries timely for a financial trading company, Infront Financial Technology. Infront processes around 24 billion events on average everyday, which translates to roughly 300,000 events per second [1]. One of the core mechanisms of DSP for meeting such high performance requirements is to split the data and use resource parallelism to deal with high loads.…”