Jyoti Nigania

Hi,i am writing blogs for our platform House of Bots on Artificial Intelligence, Machine Learning, Chatbots, Automation etc after completing my MBA degree. ...

Full Bio 

Hi,i am writing blogs for our platform House of Bots on Artificial Intelligence, Machine Learning, Chatbots, Automation etc after completing my MBA degree.

A Strong Determination Of Machine Learning In 2K19
16 days ago

Data Science: A Team Spirit
23 days ago

If You Are A Beginner Then Have Handy These Machine Learning Books To Gain Knowledge
24 days ago

Industry Automation Is Gearing Up Various Companies
26 days ago

Perks Of Becoming A Big Data Engineer Highlighted In A YouTube Video
32 days ago

These Computer Science Certifications Really Pay Good To You
117711 views

List Of Top 5 Programming Skills Which Makes The Programmer Different From Others?
115179 views

Which Programming Language Should We Use On A Regular Basis?
106347 views

Cloud Engineers Are In Demand And What Programming Language They Should Learn?
86520 views

Python Opens The Door For Computer Programming
65712 views

Is Machine Learning in Finance really different from Machine Learning in other Fields?

By Jyoti Nigania |Email | Jul 26, 2018 | 6666 Views

How is Machine Learning in finance different from Machine Learning in other fields?

Answered by Igor Halperin on Quora:
In my view, the main differences stem from differences in data. In finance, data are (very) noisy, and often non-stationary. 'Signals' cannot be split from 'noise' in any unique way, as a matter of principle. This is very different from, say, image processing, where the level of noise can be controlled, at least in principle. Also, the notion of non-stationary data is non-existent for image processing. Because of a pronounced role of noise, some machine learning models, for example non-probabilistic models, are not very useful in finance.

The other difference is the amount of data. Many interesting problems of finance are problems with small-to-medium datasets, which makes applications of data-hungry methods such as deep learning problematic. Therefore, in finance enforcing some prior knowledge is often necessary, via (depending on a method used) choices of regularization, Bayesian priors, or other general principles such as analysis of symmetries.

One more important difference is that the 'true' state space in finance is not well defined. There are so-called black swan events-things that are outside of financial models, for example political risk, that nevertheless might have severe impact on security prices. There is a difference between uncertainty and probability (risk). Most machine learning models (as well as most of classical financial models) deal with probabilistic systems with a well defined state space, they do not admit black swans. They are models of risk but not models of uncertainty. 

Source: HOB