The leading knowledge platform for the financial technology industry
The leading knowledge platform for the financial technology industry

A-Team Insight Blogs

Intelligent Trading Summit: An Architecture for Intelligent Trading

A-Team Group’s Intelligent Trading Summit dedicated to discovering What’s Next for Data Driven Trading Technology got underway with an inspiring opening keynote presentation from Alessandro Petroni, senior principal architect, financial services, at Tibco Software. Petroni discussed the need for intelligent trading, the challenges it presents and the value it offers. He also described the management of Big Data in motion and outlined a potential architecture for intelligent trading.

Petroni was introduced to conference delegates by Andrew Delaney, editor-in-chief at A-Team Group, who noted that low latency alone is no longer enough to provide competitive advantage. Instead, he proposed the need for Big Data and fast analytics, which are emerging as key elements in the next generation of data driven trading technologies.

Petroni picked up on these points, saying: “High frequency and algo trading are not enough to stay competitive in an increasingly complex cross-asset and cross-location market challenged by the pressure of compliance. To carve out profit, something else is needed beyond speed. The challenge is to build innovative solutions that get ideas into the market more quickly and help traders understand threats and opportunities as soon as possible.”

Competitive advantage, he suggested, is based on combining information from different places and getting insight into it quickly. The information needs to be both historical and real-time to provide context. A platform for processing the information should be the result of stakeholder collaboration and deliver business value by building apps faster, rather than delivering faster apps. This would mean new algo strategies could be available in hours, not days or weeks.

Petroni explained: “This is all about information from customers, the ability to capture the intelligence of subject matter experts and put it in the platform. Information needs to come from exchanges and partners, it must be more than market data, and it must begin to include social data from sites such as Twitter and Facebook for sentiment analysis. Machine data could also contribute to trading strategies.”

Tibco has built a platform for intelligent trading by combining collaborative people, information and systems. The aim of the platform is to shift how strategy is built to deliver on the fly strategy and strategy changes, perhaps responding immediately to a trading strategy that is not making money by adjusting the model and deploying a new strategy on the fly.

If this is one of the intended outcomes of the platform, it must be supported by Big Data in motion, although Petroni warns that while input is important for trading, more important are system outcomes. He said: “We need to add value of data and veracity of data to the three Vs of Big Data, namely volume, velocity and variety. The veracity of data and its quality are problems that must be solved. As we want to process data on the fly, we need to cleanse it as it enters the system, an issue that is being addressed.”

Turning to the architecture needed to support analysis of Big Data in motion, which can deliver trades that are not only fast, but also intelligent in terms of being most profitable while carrying least risk, Petroni outlined the need for a component-based system run across a distributed network. The necessary components include connectors for incoming data streams from many sources, a real-time ultra-low latency event bus to connect components, an in-memory shared data grid for fast delivery of data to apps, a real-time event processing engine, trading applications and gateways including risk control mechanisms, and dashboards for all-important human interaction with the system.

He concluded: “The need is for a highly scalable framework that can bring information into the system in real time and perform predictive analytics on the data. The outcome is a signal to the trader or risk manager of threats or opportunities in trading. For example, the signal could indicate fraudulent behaviour and flag the need to stop trading, or it could provide confidence around the accuracy of a strategy and promote the feeding of trades into the market.”

Related content

WEBINAR

Recorded Webinar: Approaches to migrating market data to the cloud to drive agility in trading operations

Market data in the cloud is an attractive proposition in terms of reducing the cost of on premise servers and storage, and moving into a more agile and flexible data delivery environment. It is also well suited to working from home, the fall-back of many financial institutions during lockdowns caused by the coronavirus pandemic. But...

BLOG

NeoXam Partners with MDP to Grow Market Data Footprint in DACH Region

Paris-based data management platform provider NeoXam has forged an alliance with MDP – a new market data consultancy founded by former executives of Screen Group, now part of TRG Screen – to extend the reach of its DataHub platform in the DACH region comprising Germany, Austria and Switzerland. The initiative will focus on helping clients...

EVENT

RegTech Summit APAC Virtual

RegTech Summit APAC will explore the current regulatory environment in Asia Pacific, the impact of COVID on the RegTech industry and the extent to which the pandemic has acted a catalyst for RegTech adoption in financial markets.

GUIDE

Regulatory Data Handbook – Fifth Edition

In response to the popularity of the A-Team Regulatory Data Handbook, we have published a fifth edition outlining the essentials of regulations that are likely to have an impact on data and data management at your organisation. New to this edition is a section on RegTech, covering drivers behind the development of innovative regulatory technology,...