Deep Learning for Trading Part 1: Can it Work?

In the last few years, deep learning has gone from being an interesting but impractical academic pursuit to a ubiquitous technology that touches many aspects of our lives on a daily basis – including in the world of trading. This meteoric rise has been fuelled by a perfect storm of:

• Frequent breakthroughs in deep learning trading research which regularly provide better tools for training deep neural networks
• An explosion in the quantity and availability of data
• The availability of cheap and plentiful compute power
• The rise of open-source deep learning tools that facilitate both the practical application of the technology and innovative research that drives the field ever forward

Deep learning excels at discovering complex and abstract patterns in data and has proven itself on tasks that have traditionally required the intuitive thinking of the human brain to solve. That is, deep learning is solving problems that have thus far proven beyond the ability of machines.
Therefore, it is incredibly tempting to apply deep learning to the problem of forecasting the financial markets. And indeed, certain research indicates that this approach has potential. For example, the Financial Hacker found an edge in predicting the EUR/USD exchange rate using a deep architecture stacked with an autoencoder. We previously compared the performance of numerous machine learning algorithms on a financial prediction task, in Machine Learning for Trading, and deep learning was the clear outperformer.

Deep Learning for Trading? Not so fast…

However, as anyone who has used deep learning in trading can attest, the problem is not nearly as simple as just feeding some market data to an algorithm and using the predictions to make trading decisions. Some of the common issues that need to be solved include:

1. Working out a sensible way to frame the forecasting problem, for example as a classification or regression problem.
2. Scaling data in a way that facilitates the training of the deep network.
3. Deciding on appropriate network architecture.
4. Tuning the hyperparameters of the network and optimization algorithm such that the network converges sensibly and efficiently. Depending on the architecture chosen, there might be a couple of dozen hyperparameters that affect the model, which can provide a significant headache.
5. Coming up with a cost function that is applicable to the problem.
6. Dealing with the problem of an ever-changing market. Market data tends to be non-stationary, which means that a network trained on historical data might very well prove useless when used with future data.
7. There may be very little signal in historical market data with respect to the future direction of the market. This makes sense intuitively if you consider that the market is impacted by more than just its historical price and volume. Further, pretty much everyone who trades a particular market will be looking at its historical data and using it in some way to inform their trading decisions. That means that market data alone may not give an individual much of a unique edge.

The first five issues listed above are common to most machine learning problems and their resolution represents a big part of what applied data science is all about. The implication is that while these problems are not trivial, they are by no means deal-breakers.
On the other hand, problems 6 and 7 may very well prove to thwart the best attempts at using deep learning to turn past market data into profitable trading signals. No machine learning algorithm or artificial intelligence can make good future predictions if its training data has no relationship to the target being predicted, or if that relationship changes significantly over time.¹

Said differently, feeding market data to a machine learning algorithm is only useful to the extent that the past is a predictor of the future. And we all know what they say about past performance and future returns.

In deep learning trading systems that I’ve taken to market, I’ve always used additional data. Not just historical, regularly sampled price and volume data and transformations thereof. While there does appear to be a slim edge in using deep learning to extract signals from past market data, that edge may not be significant enough to overcome transaction costs. And even if it does, it may not be significant enough to justify the risk and effort required to take it to market. On the other hand, supplementing historical market data with innovative, uncommon data sets has proven more effective – at least in my experience. ²
In this series of posts, we explore and compare various deep learning trading tools and techniques in relation to market forecasting using the Keras package. We will do so using only historical market data, so the results need to be interpreted considering the discussion above.
We expect deep learning to uncover a slim edge using historical market data, but the purpose of this analysis is to compare different deep learning tools in relation to market forecasting, not necessarily to build a market-beating trading system. That I leave to you – perhaps you can supplement the models we explore here with some creative or uncommon data or other tools to find a real edge.

What is Keras?

Keras is a high-level API for building and training neural networks. Its strength lies in its ability to facilitate fast and efficient research, which of course is very important for systematic traders, particularly those of the DIY persuasion for whom time is often the limiting factor to success. Keras is easy to learn and its syntax is particularly friendly. Keras also plays nicely with CPUs and GPUs and can integrate with the TensorFlow, Theano and CNTK backends – without limiting the flexibility of those tools. For example, pretty much anything you can implement in raw TensorFlow, you can also implement in Keras, likely at a fraction of the development effort.
Keras is also implemented in R, which means that we can use it directly in any trading algorithm developed on the Zorro Automated Trading Platform, since Zorro has seamless integration with an R session.³

What’s next?

In the deep learning trading experiments that follow in Part 2 and beyond, we’ll use the R implementation of Keras with TensorFlow backend. We’ll be exploring fully connected feedforward networks, various recurrent architectures including the Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), and even convolutional neural networks which normally find application in computer vision and image classification.

Notes:
1. The latter problem is known as covariate shift. Calling it a deal-breaker is not necessarily accurate since there are methods for detecting it and, sometimes, dealing with it.
2. In our Advanced Algorithmic Trading course, we have a unit dedicated to the acquisition of one such innovative and uncommon (and free) data set. You can apply the principles in that unit to acquire other data sets according to your own innovation and creativity. Learn about our algorithmic trading courses here.
3. In our Advanced Algorithmic Trading course, we go into great detail about setting up Zorro’s interface with R, and provide numerous examples of using it to build quant-style trading strategies.

Originally posted on Robot Wealth Blog.