Can you predict the future?
Daily, G-Research apply scientific techniques to find patterns in large, noisy and rapidly changing real-world data sets with the goal to predict the future of financial markets.  Using machine learning modelling techniques, robust statistical analysis and pattern recognition, our data scientists work to beat the efficient market hypothesis.
We have put together what we hope will be an interesting and fun forecasting challenge to provide you with a flavour of one of the types of problems we work on here at G-Research.
The Challenge
We’d like you to predict y (an element of the return of a financial data series) from a number of features we’ll supply you with. You can download a training data set and some example solutions from our website.
You have three months to train, test and submit your models. We’ll keep a leader board of public scores live on our website so you can track your model’s performance on a portion of the test data.
We’ll then score all the final models on the remainder of the test data set to determine the winner.
Win $30,000
Start here:
Submission deadline: 15th April 2018
Any questions please contact challenge