Noisy data is one of the biggest risks when applying machine learning to stock selection, according to two quants trying to tackle the problem.
Keywan Christian Rasekhschaffe, senior quantitative strategist at commodity trading giant Gresham Investment Management, says feature engineering – organising data to increase the signal-to-noise ratio and make it easier for machine learning algorithms to interpret – is the most fruitful way to reduce the risk of false signals, otherwise known as
- Libor leaders: ABP crafts blueprint for corporate Libor switch
- Libor leaders: how seven firms are tackling the transition
- Libor replacement: a modelling framework for in-arrears term rates
- Swaps data: a new era of competition in interest rate futures
- Libor leaders: EIB sees prizes and pitfalls in Libor reform