Optiver, a leading global market maker, announces the launch of its first data science competition. Hosted in partnership with Kaggle, the world’s largest data science and machine learning community, Optiver’s challenge invites the global community to explore the principles of volatility and its integral role in the financial market. The big-data competition builds on the firm’s culture of embracing fresh perspectives and innovative ideas from diverse backgrounds.
“Trading automated and at scale is a fascinating data challenge,” says Optiver Partner and Delta1 Lead, Andrew Meyer. “Our Amsterdam office has captured 1 PB of market data alone. Our traders, researchers and engineers are collaborating daily on which problems to solve, how and why. Kaggle has more than seven million registered data scientists trying to solve the most difficult data problems and some of our best hires are from the community. It therefore feels natural to engage more broadly with the Kaggle community by sharing one of our realistic challenges.”
Optiver contributes to efficient, transparent and healthy markets by accurately pricing financial instruments including options, ETFs, cash equities, bonds and foreign currencies on exchanges around the world. In order to continuously generate accurate Option prices for end-investors, the firm builds and relies on sophisticated volatility models. Optiver’s algorithmic approach is always evolving, and the company is eager to explore what the Kaggle community can contribute.
“As a company, we are always seeking new perspectives,” says Optiver US CEO, Rutger Brinkhuis. “We want data scientists spanning all fields, experience levels and walks of life to put their skills to the test. Optiver believes the greatest ideas can come from unexpected places. Upcoming talent from the next generation of data scientists could very well come up with the best algorithm. No matter their background, these are the minds Optiver wants to know.”
Over the course of the three-month challenge, individuals and teams will build models that predict short-term volatility for hundreds of stocks across different sectors. Participants will be provided millions of rows of highly granular financial data, with which they will have the freedom to develop and experiment. Models will be evaluated against real market data in the three-month evaluation period after submission, with the winning approaches awarded $100k in total prize money.
To sign up to participate, please visit: https://www.kaggle.com/c/optiver-realized-volatility-prediction.
For more such updates and perspectives around Digital Innovation, IoT, Data Infrastructure, AI & Cybsercurity, go to AI-Techpark.com.