Cleaning noisy data ‘almost 70%’ of machine learning labour

Quants flag signal-to-noise ratio as key to reducing overfitting risk

Do not adjust your set: improving data signal is a priority for quants

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

Only users who have a paid subscription or are part of a corporate subscription are able to print or copy content.

To access these options, along with all other subscription benefits, please contact [email protected] or view our subscription options here:

You are currently unable to copy this content. Please contact [email protected] to find out more.

To continue reading...

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: