Risk Analysis — Fast

ScaleOut’s In-Memory Computing Accelerates Risk Analysis

Reducing Risk Analysis from 15 Minutes to 1 Second

A Case Study

To maintain a competitive edge, financial firms must be able to review their investment strategies in real time during the trading day. For example, a hedge fund that employs a “pairs trading” strategy typically has thousands of long and short equity positions that may require rebalancing as the market constantly re-prices these equities throughout the trading day.

In-memory computing technology provides the speed and scalability needed to immediately identify positions that need rebalancing. ScaleOut Software has developed a proof-of-concept application that demonstrates the power of in-memory computing for real-time risk analysis.

“Every hedge fund needs this solution.”
— Chief Software Architect

Learn about the Application

This paper describes the proof of concept in detail, including code samples.


Watch the Demo

Launch this short video to see this sample app run 40X faster than batch-scheduled Hadoop.


Try out the Sample Application

Download the Java or .NET sample app.


The Challenge

A large hedge fund in New York employs more than a thousand different equity investment strategies that are constructed using a pairs trading model. To determine whether a given strategy has deviated from its business rules, the company currently uses a relational database to store its positions and analyze this data as market prices change during the trading day. Although timeliness of the analysis has a huge impact on profits, the company can only obtain response times of about fifteen minutes using the relational database. Since investment markets can experience significant fluctuations within fifteen minutes, traders often need to eyeball market fluctuations and make trading decisions. The fund needs the ability to analyze its equity positions at market-speed, instantly alerting traders when a strategy goes out of range and enabling timely trades.

The Solution: In-Memory Computing

Using scalable, in-memory computing, ScaleOut ComputeServer provides the operational intelligence required to deliver timely results for the company’s traders. To demonstrate the power and simplicity of in-memory computing, ScaleOut Software has developed a sample application (which can be downloaded below) as a proof of concept. The application holds the equity positions and parameters of the company’s hedging strategies within a scalable, in-memory data grid. Using an integrated, in-memory compute engine, it updates all equity positions every second from a stream of simulated market data and evaluates the rules for each strategy to determine if action is needed. It combines the results into a stream of alerts delivered to the traders using a graphical display.

The following figure shows the components and data flow of the application. Note that the hedge fund’s data is analyzed in place within the in-memory data grid; a separate analytics platform is not required.


Using ScaleOut ComputeServer for Real-Time Risk Analysis

This application demonstrates that thousands of strategies can be analyzed in less than a second instead of fifteen minutes required for a relational database. Automatic alerting in real time relieves traders of the burden to continuously monitor the status of their strategies, enabling them to operate the fund much closer to market-speed, optimize its performance, and maximize profits.

Download the Sample App

We invite you to download the sample application and try it out on either a Linux or Windows workstation. The download includes the binaries needed to run the application, together with a detailed description of its design and instructions.

To run the application you also will need to download an evaluation copy of ScaleOut ComputeServer for use on a single computer. To evaluate scaling larger workloads across multiple servers, please feel free to contact us at [email protected] to obtain a multiple server license key for evaluation purposes.

Try ScaleOut for free

Use the power of in-memory computing in minutes on Windows or Linux.

Try for Free

Not ready to download?