24 hours to create innovative alpha generating models using the latest ML and Quant techniques inside BlackRocks office
Algothon, the largest quant finance hackathon in Europe, is returning this year with BlackRock on the 19th and 20th of October inside their London Office!
You can expect:
- Exclusive alternative data and core data.
- Machine Learning & Deep RL workshops.
- Talks from leading academics and BlackRock Researchers.
- Free Snacks, Restaurant meals, Swag and T-Shirts.
- Prizes (To Be Announced, last year's included: iPads, $8000 AWS credits, super car driving experiences)
£12,776 in prizes
1st Overall - iPad Pro & $1250 AWS credits for the team
The overall winner for the best Alpha gen idea. Sponsored by BlackRock: https://careers.blackrock.com/
2nd Overall - Bose Wireless Headphones & $1250 AWS credits for the team
The second place project for the best Alpha gen idea. Sponsored by BlackRock: https://careers.blackrock.com/
3rd Overall - 4K monitors & $1250 AWS credits for the team
The third place project for the best Alpha gen idea. Sponsored by BlackRock: https://careers.blackrock.com/
Best use of AWS
Prize for the best use of AWS in the hackathon. Sponsored by AWS educate: https://www.awseducate.com
Best Climate Finance & Investment Hack
Prize for the best climate finance project. The model that best addresses the risks posed by the climate and investment solutions to positively impact the climate. Sponsored by Imperial College Centre for Climate Finance and Investment: https://www.imperial.ac.uk/business-school/faculty-research/research-centres/climate-finance-investment/
Submitting to this hackathon could earn you:
Everyone is welcome to apply, provided you meet the criteria below:
- Must be over 18 years of age
- Applications must be made through: http://2019.algothon.org/
Dr Anastasiya Ostrovnaya
Imperial College Centre for Climate Finance
Prof. Emma McCoy
Imperial College London
Dr Alexander Remorov
Justin R. Peterson
Dr George Poyiadjis
What is the Alpha gen potential of the tool/ model?
How much alpha does this tool have the potential to? Better Sharpe ratio score higher. Teams need to be able to demonstrate the effectiveness of their tool made in the hackathon on out of sample data to justify their reasoning for alpha gen potential.
How viable is it to fully implement the tool/ model into a real system?
An idea of how to implement the idea in a real-world environment and potential difficulties that could occur; this can include the cost of technology required, the cost to run, the time required to implement and how autonomous the system is?
How original is the idea?
Is this an original idea? What research has been done in this area? What was the inspiration for their idea?
How expandable is the idea? (more general ideas are better)
How expandable the idea is to different use cases, is it specific to only one forecast or is it a system that provides its own forecasts. Is it specific to one security type or can the strategy be applied to make different types of securities?
How will this performance in different market conditions?
How the system will respond in different market environments such as bear and bull markets, the risks the system is open too, how the system will respond to events such as flash crashes or periods of very low volatility?
- Machine Learning/ AI