Benchmark Solutions Announces Bond Trade Price Challenge via Kaggle Competition

Share Article

Contest designed to develop models to accurately predict the trade price of a bond

“Accurate bond pricing has always been hindered by the lack of liquidity and transparency in the market,” said Jim Toffey, CEO of Benchmark Solutions.

Benchmark Solutions, a next-generation financial intelligence firm, today announced its Benchmark Bond Trade Price Challenge, a competition running on Kaggle, where competitors use Benchmark’s unique data to try to predict the next price at which a US corporate bond might trade. To date, the Benchmark Bond Trade Price Challenge has garnered 138 teams for a total of 249 players and 1,072 entries. The competition, which is still open to entrants, will run through Monday, April 30, with the top 3 winning individuals or teams sharing a prize of $17,500.

Historically, there has been a huge gap in the availability of reference information for investors trading corporate bonds, a stark contrast with the equities markets where real-time information is readily available. This lack of credible, relevant and accurate market data for the OTC fixed income markets has rendered the US corporate bond market particularly illiquid. The Benchmark Bond Trade Price Challenge requires competitors to design algorithms to improve upon Benchmark’s pricing, using only a static data set. Each submission’s performance will be evaluated using mean absolute error. In order to be judged as one of the winners, participants are required to provide code, as well as a description of their algorithm in document form.

“Accurate bond pricing has always been hindered by the lack of liquidity and transparency in the market,” said Jim Toffey, CEO of Benchmark Solutions. “As the first provider of unbiased, real-time corporate bond prices, we are aiming to level the playing field for bond traders allowing them to make better investment decisions. This competition is designed to challenge bright minds to develop models that accurately predict the trade price of a US corporate bond.”

“We are extremely pleased that a revolutionary financial technology company like Benchmark Solutions turned to our community of data scientists to produce the best solutions,” said Anthony Goldbloom, chief executive officer, Kaggle. “We work diligently to connect organizations to the advanced machine learning and statistical techniques that would allow them to extract maximum value from their data.”

Kaggle is a platform for data prediction competitions that allows organizations to post their data and have it scrutinized by the world's best data scientists. In exchange for a prize, winning competitors provide the algorithms that beat all other methods of solving a data-crunching problem. Most data problems can be framed as a competition. Find out more or enter the Benchmark Bond Trade Price Challenge.

In addition, both Toffey and Benchmark’s Chief Scientist Peter Cotton will be speaking at the upcoming Stanford University’s 3rd Conference in Quantitative Finance, March 30-31, 2012, in Stanford, CA., about the current state of the OTC fixed income markets and related issues including risk management, market microstructure, high-frequency data, modeling, and assimilation. Leading competitors will be invited to join the conference and give a short description of some of the methods they have employed to model the data.

Notes to Editors

Benchmark Solutions was founded in the wake of the credit crisis in September 2009 to address fundamental shortcomings in price transparency and independence in the fixed income and derivatives markets – a multi-trillion market that currently trades in the dark with little or no real-time pricing data for a majority of its assets. Backed by Warburg Pincus and led by CEO, Jim Toffey (Founder and CEO of Tradeweb), Benchmark has spent two years and significant financial investment in technology and human capital to solve this problem. Benchmark is headquartered in New York. For more information, please visit

# # #

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Oksana Poltavets
Email >
Visit website