|
|
Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks |
Abstract
"We use an autoencoder composed of stacked restricted Boltzmann machines to extract features from the history of individual stock prices. Our model is able to discover an enhanced version of the momentum effect in stocks without extensive hand-engineering of input features and deliver an annualized return of 45.93% over the 1990-2009 test period versus 10.53% for basic momentum."
|
Working Paper, Stanford University, December 12, 2013-Lawrence Takeuchi, Yu-Ying (Albert) Lee
09.09.2015
|
|
|
|
|
Themes
Asia
Bonds
Bubbles and Crashes
Business Cycles Central Banks
China
Commodities Contrarian
Corporates
Creative Destruction Credit Crunch
Currencies
Current Account
Deflation Depression
Equity Europe Financial Crisis Fiscal Policy
Germany
Gloom and Doom Gold
Government Debt
Historical Patterns
Household Debt Inflation
Interest Rates
Japan
Market Timing
Misperceptions
Monetary Policy Oil Panics Permabears PIIGS Predictions
Productivity Real Estate
Seasonality
Sovereign Bonds Systemic Risk
Switzerland
Tail Risk
Technology
Tipping Point Trade Balance
U.S.A. Uncertainty
Valuations
Yield
|