Open Salon: FINANCIAL ML

Reinforcement Learning for Portfolio Management

Problem definition:

1. Based on pre-opening signals achieve daily Sharpe ratio close to 1 for a directional trade in SPY

2. Use Atari and Go game winning strategy
Demis Hassabis ‏@demishassabis (see later deepmind post)

Modern Portfolio Theory states that adding assets to a diversified portfolio that have correlations of less than one with each other can decrease portfolio risk without sacrificing return. Such diversification will serve to increase the Sharpe ratio of a portfolio.

Sharpe ratio = (Mean portfolio return − Risk-free rate)/Standard deviation of portfolio return

The ex-ante Sharpe ratio formula uses expected returns while the ex-post Sharpe ratio uses realized returns.

Read more: Sharpe Ratio Definition | Investopedia http://www.investopedia.com/terms/s/sharperatio.asp#ixzz4C15w8pDI

AQR Funds
https://funds.aqr.com/

MSCI, A LEADER IN FACTOR INDEXING
https://www.msci.com/factor-indexes

ALGORITHMIC TRADING

Classification-Based Financial Markets Prediction Using Deep Neural Networks

Matthew Francis Dixon
Illinois Institute of Technology – Stuart School of Business, IIT

Diego Klabjan
Northwestern University

Jin Hoon Bang
Northwestern University

May 18, 2016

Abstract:

Deep neural networks (DNNs) are powerful types of artificial neural networks (ANNs) that use several hidden layers. They have recently gained considerable attention in the speech transcription and image recognition community for their superior predictive properties including robustness to over fitting. However their application to algorithmic trading has not been previously researched, partly because of their computational complexity. This paper describes the application of DNNs to predicting financial market movement directions. In particular we describe the configuration and training approach and then demonstrate their application to back testing a simple trading strategy over 43 different Commodity and FX future mid-prices at 5-minute intervals. All results in this paper are generated using a C++ implementation on the Intel Xeon Phi co-processor which is 11.4x faster than the serial version and a Python strategy back testing environment both of which are available as open source code written by the authors.

http://www.valuewalk.com/2016/06/classification-based-financial-markets-prediction-using-deep-neural-networks/
-----------------------------