Predicting asset prices is extremely difficult, even for sophisticated machine learning models. Data science typically succeeds where there are complex behaviors which can be described in data and where consistent inputs lead to consistent “predictable” outcomes; machine learning techniques cannot magically make “signal” appear out of thin air, nor can they make unstable factors more stable.
Nevertheless, there are a number of useful characteristics that set apart machine learning techniques from the traditional quantitative and ‘quantamental’ investing toolbox, and automated machine learning is a compelling proposition for modern quantitative investors.
In this session, Russell Smith, FactSet’s risk and quantitative analytics specialist and Peter Simon, DataRobot’s lead data scientist for financial markets, will explore how modern automated machine learning techniques add value to the quantitative investment process.
In this webinar you will learn:
- How data science can augment ‘traditional’ quant approaches
- How automated machine learning enables quantitative researchers to efficiently explore larger problem spaces
- How quantitative investors can benefit from the seamless integration of DataRobot’s powerful automated machine learning capabilities into the FactSet ecosystem
Speakers:
