“Optimizing trading strategies without overfitting” by Dr. Ernest Chan – QuantCon 2018

Channel	Publish Date	Thumbnail & View Count	Download Video
	Publish Date not found	0 Views	View on YouTube Download Video

Optimizing the parameters of a trading strategy through backtesting has one major problem: there are usually not enough historical trades to achieve statistical significance. This talk will discuss several methods to overcome this problem, including stochastic control theory and simulations. Simulations can involve either linear or nonlinear time series models such as recurrent neural networks.

About the speaker:
Dr. Ernest Chan is a managing member of QTS Capital Management, LLC., a commodity pool operator and trading advisor. He began his career as a machine learning researcher with IBM's Human Language Technologies Group and later joined Morgan Stanley's Data Mining Group. He has also been a quantitative researcher and proprietary trader for Credit Suisse. Ernie is the author of "Machine Trading," "Algorithmic Trading," and "Quantitative Trading," all published by Wiley, and a popular financial blogger at epchan.blogspot.com. He also teaches in the Master of Science in Predictive Analytics program at Northwestern University. He received his Ph.D. in theoretical physics from Cornell University.

The slides for this presentation can be found at http://bit.ly/2HWCFxC.

To learn more about Quantopian, visit http://www.quantopian.com.

Disclaimer
Quantopian provides this presentation to help people write trading algorithms. It is not intended as investment advice.

More specifically, the material is for informational purposes only and does not constitute an offer to sell or a solicitation to buy, a recommendation or endorsement of any security or strategy, nor does it constitute an offer by Quantopian to provide investment advice or other services.

In addition, the Content does not constitute investment advice nor does it offer an opinion regarding the suitability of any security or any particular investment. Quantopian does not guarantee the accuracy or completeness of the views expressed on the Site. The views may change and may become unreliable for a variety of reasons, including changes in market conditions or economic circumstances.