Quantnews Monthly Digest | June Issue
Your monthly news & research update for all things quant trading
This month, Quantnews partnered with systematic trader Rob Carver* to learn about his unique backtesting method to avoid overfitting, featured a guest contributor from the quant finance think tank Thalesians^, and interviewed the founder of Cuemacro^ about his unique approach to the macro markets.
Rob Carver*, an independent systematic futures trader, writer and research consultant, sits down with Quantnews to discuss backtesting, curve fitting, and how using a trading system can help traders avoid common emotional trading mistakes like fear and greed.
- Learn about three types of overfitting – implicit, explicit, and tacit — and how to avoid them
- Rob discusses how and why he uses fake data to backtest new systems before deploying
- See why the Sharpe ratio is not the metric of choice for evaluating his trading systems, and find out what is
Read or listen to this exclusive interview!
New this month
INTERVIEW: Saeed Amen of Cuemacro on FX, Alternative Data, and Backtesting
Founder and CEO of Cuemacro Saeed Amen sits down with QuantNews to discuss his passion for the macro markets and his systematic trading strategies. He explains how alternative data is gaining traction and his personal method of attack when it comes to finding and analysing unstructured data, including machine learning. Read on to find out more about data, machine learning, and Amen’s open-source backtesting tools.
WEBINAR: Machine Learning for Trading: Part 3
In the final part of this 3-part series, you will learn how to tune the properties of your machine learning algorithm to achieve better performance. In this series, quantitative trader Trevor Trinkino gives traders a step-by-step introduction on using machine learning to create a trading algorithm using Python. Watch this lesson on demand now. Miss part 1 and part 2? Watch now.
RESEARCH: Fundamentals of Machine Learning
This month, Ivan Zhdankin of the Thalesians explores the fundamentals of a machine learning model and discusses how an ML model differs from a more traditional statistical or econometric model. Read this article to learn why notions such as bias-variance trade off, bootstrapping, under/overfitting and more are essential to understand when creating a machine learning model.
Live Webinar: The 7 Reasons Most Machine Learning funds Fail
3 July 2018 | 13:00 – 14:00 BST (GMT+1)
Marcos López de Prado*, founder of www.QuantResearch.org and True Positive Technologies^ has partnered with QuantNews to provide a webinar based on his popular research identifying why most machine learning funds fail. Attend this webinar and use his research to enhance your trading strategy and avoid potential pitfalls of machine learning.
Questions about the event? Contact us at firstname.lastname@example.org
Questions or comments? Email us at email@example.com.
Risk Warning: The FXCM Group does not guarantee accuracy and will not accept liability for any loss or damage which arise directly or indirectly from use of or reliance on information contained within the webinars. The FXCM Group may provide general commentary which is not intended as investment advice and must not be construed as such. FX/CFD trading carries a risk of losses in excess of your deposited funds and may not be suitable for all investors. Please ensure that you fully understand the risks involved.