Reinforcement Learning for Portfolio Allocation
Reinforcement learning is a machine learning approach concerned with solving dynamic optimization problems in an almost model-free way by maximizing a reward function in state and action spaces. This property makes it an exciting area of research for financial problems.
This paper demonstrates the application of reinforcement learning to create a financial model-free solution to the asset allocation problem, learning to solve the problem using time series and deep neural networks. We demonstrate this on daily data for the top 24 stocks in the US equities universe with daily rebalancing. We use a deep reinforcement model on US stocks using different deep learning architectures.
Deep Learning in Finance
Deep Learning has given excellent results fields of image recognition, speech recognition or sentiment analysis we see that these models are capable of learning from large scaled unlabelled data, forming non-linear relationships, forming recurrent structures and can be easily tweaked to avoid over-fitting.
In this research piece we see why the financial models fail and how deep learning can bridge the gap. Further on, we present three use cases for deep learning in Finance and evidence of the superiority of these models.
Regime Modelling for Optimal Allocation
Financial markets change their behaviours abruptly. The mean, variance and correlation patterns of stocks can vary dramatically, triggered by fundamental changes in macroeconomic variables, policies or regulations. A trader needs to adapt her trading style to make the best out of the different phases in the stock markets. Similarly, an investor might want to invest in different asset classes in different market regimes for a stable risk adjusted return profile.
Here, we explore the use of State Switching Markov Autoregressive models for identifying and predicting different market regimes loosely modeled on the Wyckoff Price Regimes of accumulation, distribution, advance and decline. We explore the behaviour of various asset classes and market sectors in the identified regimes.