STAC Report: Hadoop Streaming and STAC-A3

First audited STAC-A3 results demonstrate simulation scalablity

4 March 2016

Today STAC released audited STAC-A3 Benchmark results for a system running Python code via Hadoop Streaming on Cloudera Enterprise 5.4 with Dell PowerEdge servers and Intel Xeon E5-2680 v3 (Haswell) processors. The configuration details, implementation code, and test-harness software are available to premium members.

STAC-A3 simulates workloads common in the backtesting of trading strategies. Backtesting is a rate-limiting step in a firm's response to changing market conditions, so the performance of backtesting infrastructure has a top-line impact.

Several trading firms drove the requirements for STAC-A3 in order to facilitate software and hardware comparisons. Like other STAC Benchmarks, STAC-A3 is agnostic to architecture. While some firms use a shared-storage architecture for backtesting, some have turned to shared-nothing architectures like Hadoop. 

The Hadoop Streaming implementation tested in this project was authored by Think Big Analytics. Its main purpose is to produce output (algorithm P&Ls) for validating the output of other systems tested in the future. However, the first audited STAC-A3 results make this system a performance baseline against which to measure future solutions. The solution wasn't highly optimized but nevertheless demonstrated that Hadoop Streaming can scale with respect to both simulations and symbols per simulation.

Think Big also wrote the reference implementations for STAC-A3. We'd like to thank them for lending their expertise to the test framework for a big data workload that is crucial to so many financial firms.

A Spark-based implementation of STAC-A3 is also under development by Intel. STAC can make the Spark code available to premium members on request.

STAC-A3 work is ongoing. If you'd like to be involved, please let us know at the STAC Backesting SIG site.

If your firm does not have access to these materials, please take a minute to learn about subscription options.

About STAC News

Read the latest about research, events, and other important news from STAC.

Subscribe to notifications of research, events, and more.

Enter your email above, then click "Sign Up" to join the STAC mail list and (optionally) register to access materials on the site. Click for terms.