Building Stock Trading Strategies: 20% Faster with Hadoop

by Sofia ParfenovichAugust 16, 2013

Learn how the technology improves the trading system’s performance and increases customer's revenues by 12% without additional investments.

Table of Contents

Speeding up a stock trading platform

Based on complex mathematical algorithms, automated stock trading solutions take into account hundreds of factors and suggest the right time for placing buy/sell orders. Some of the systems like that can even make a deal without any human involvement. However, if an algorithm omits essential market parameters, this may bring a significant loss.

Clustering/grouping trading strategies with k-means

In this guest blog post, experts at Altoros shared a real-life example of how Hadoop and data clustering speeded up stock the performance of a trading system by 20% and increased customer’s revenues by 12%.

Improving the trading system with Hadoop and k-means

The article also explores how data clustering helped to diversify sell/buy strategies, and how the right infrastructure can improve the system’s performance without additional investments.

About the author

Sophia Parfenovich is Data Scientist at Altoros. She is interested in creating association rules for mining large volumes of data with Hadoop and other MapReduce tools. Sofia has strong experience in time-series forecasting, building trading strategies, and data analysis.

The blog post was written by Sofia Parfenovich and edited by Alex Khizhniak.

Posted In

Tags

Research and Development

Posted by:

Alex Khizhniak is Director of Technical Content Strategy at Altoros and a cofounder of a local Java User Group. Managing distributed teams since 2004, he has gained experience as a journalist, an editor-in-chief, a technical writer, a technology evangelist, a project manager, and a product owner. Alex is obsessed with AI/ML, data science, data integration, ETL/DWH, data quality, databases (SQL/NoSQL), big data, IoT, and BI. The articles and industry reports he created or helped to publish reached out to 3,000,000+ tech-savvy readers. Some of the pieces were covered on TechRepublic, ebizQ, NetworkWorld, CIO.com, etc. Find him on Twitter at @alxkh.