Search
× Search
Sunday, December 22, 2024

Archived Discussions

Recent member discussions

The Algorithmic Traders' Association prides itself on providing a forum for the publication and dissemination of its members' white papers, research, reflections, works in progress, and other contributions. Please Note that archive searches and some of our members' publications are reserved for members only, so please log in or sign up to gain the most from our members' contributions.

JPMorgan’s guide to machine learning in finance

photo

 James Drysdale, Founder at Winston Fox

 Tuesday, July 4, 2017

http://news.efinancialcareers.com/uk-en/285249/machine-learning-and-big-data-j-p-morgan


Print

6 comments on article "JPMorgan's guide to machine learning in finance"

photo

 Carl J. DeLisi, Managing Director at Ingenius Intelligence BNC Inc (I-Squared BNC) - Capital Solutions

 Saturday, July 8, 2017



Excellent article, a worthwile read


photo

 Ridwan Arizar, Commodities & Technology Specialist

 Saturday, July 8, 2017



And there you have it - breaking all the hype on data scientists Nr 10 statement of JPM.

10. You won’t need to be a machine learning expert, you will need to be an excellent quant and an excellent programmer

J.P. Morgan says the skillset for the role of data scientists is virtually the same as for any other quantitative researchers. Existing buy side and sell side quants with backgrounds in computer science, statistics, maths, financial engineering, econometrics and natural sciences should therefore be able to reinvent themselves. Expertise in quantitative trading strategies will be the crucial skill. “It is much easier for a quant researcher to change the format/size of a dataset, and employ better statistical and Machine Learning tools, than for an IT expert, silicon valley entrepreneur, or academic to learn how to design a viable trading strategy,” say Kolanovic and Krishnamacharc.


photo

 Yajun YAN, Credit Risk Modeling Analyst at Radian Guaranty Inc

 Sunday, July 9, 2017



Beautiful Summary! Thank you James. This topic is exactly what I frequently think about. As a credit modeler of residential mortgage, most Machine Learning Techs I heard before are about classification, which makes me a bit puzzle how things like decision tree can be used to build sound trading strategies. But I do believe it can been achived as Alpha Go arleady be able to defeat all world champions, and even their ''linear combinations''.


photo

 Rosanna Bruni, Senior Director, Trading

 Monday, July 10, 2017



Thank you. This is great. A lot of discussion around this subject lately.


photo

 Omar Filali, CEO & Founder of iDMS Investment

 Tuesday, July 11, 2017



Amazing article. Another innovation that lead the big financial institutions in the world keeping a competitive advantage .


photo

 Jonathan Prout, Over ten years experience in the investment and finance industry as a Portfolio Manager and Analyst

 Wednesday, July 12, 2017



Good article from JPM quant research team which are high quality. As I recall the Scikit learn docs have a similar scheme to aid in which class of model to use for different data environments - which is worth checking out. I'm not sure I totally agree with point 10 as people should invest real time, read papers, take courses and look at source code on Github before attempting to apply non linear models in live trading deployment. Models like SVM's are very power for classification tasks, for instance to discover new (non traditional sector based) pair trading opportunities, but if you do not understand what is going on under the hood and take great care to CV and train correctly for alpha pred - non linear models will over fit. High in-sample R2 do not mean high out of sample returns

Please login or register to post comments.

TRADING FUTURES AND OPTIONS INVOLVES SUBSTANTIAL RISK OF LOSS AND IS NOT SUITABLE FOR ALL INVESTORS
Terms Of UsePrivacy StatementCopyright 2018 Algorithmic Traders Association