# Zorro

One of the ongoing research projects inside the Robot Wealth community involves an FX strategy with some multi-week hold periods. Such a strategy can be significantly impacted by the swap, or the cost of financing the position. These costs change over time, and we decided that for the sake of more accurate simulations, we would incorporate these changes into our backtests. This post shows you how to simulate variable FX swaps in both Python and the Zorro trading automation software platform. What is Swap? The swap (also called the roll) is the cost of financing an FX position. It is typically derived from the central bank interest rate differential of the two currencies in the exchange rate being traded, plus some additional fee for your broker. Most brokers apply it on a daily basis, and typically apply three times the regular amount on a Wednesday to account for the weekend. Swap can be both credited to and debited from a trader's account, depending on the actual position taken. Why is it Important? Swap can have a big impact on strategies...

This is the third in a multi-part series in which we explore and compare various deep learning tools and techniques for market forecasting using Keras and TensorFlow. In Part 1, we introduced Keras and discussed some of the major obstacles to using deep learning techniques in trading systems, including a warning about attempting to extract meaningful signals from historical market data. If you haven’t read that article, it is highly recommended that you do so before proceeding, as the context it provides is important. Read Part 1 here. Part 2 provides a walk-through of setting up Keras and Tensorflow for R using either the default CPU-based configuration, or the more complex and involved (but well worth it) GPU-based configuration under the Windows environment. Read Part 2 here. Part 3 is an introduction to the model building, training and evaluation process in Keras. We train a simple feed forward network to predict the direction of a foreign exchange market over a time horizon of hour and assess its performance. [thrive_leads id='4507'] . Now that you can train your deep learning models on a GPU, the fun can really start....

Earlier this year, I attended the Google Next conference in San Francisco and gained some first-hand perspective into what’s possible with Google's cloud infrastructure. Since then, I’ve been leaning on Google Cloud Platform (GCP) to run my trading algorithms (and much more) and it has quickly become an important tool in my workflow! In this post, I’m going to show you how to set up a Google Cloud Platform compute instance to act as a server for hosting a trading algorithm. We'll also see why such a setup can be a good option and when it might pay to consider alternatives. Cloud compute instances are just a tiny fraction of the whole GCP ecosystem, so before we go any further, let's take a high-level overview of the various components that make up Google Cloud Platform. What is Google Cloud Platform? GCP consists of a suite of cloud storage, compute, analytics and development infrastructure and services. Google says that GCP runs on the very same infrastructure that Google uses for its own products, such as Google Search. This suite of services...

In the first Mean Reversion and Cointegration post, I explored mean reversion of individual financial time series using techniques such as the Augmented Dickey-Fuller test, the Hurst exponent and the Ornstein-Uhlenbeck equation for a mean reverting stochastic process. I also presented a simple linear mean reversion strategy as a proof of concept. In this post, I’ll explore artificial stationary time series and will present a more practical trading strategy for exploiting mean reversion. Again this work is based on Ernie Chan's Algorithmic Trading, which I highly recommend and have used as inspiration for a great deal of my own research. Go easy on my design abilities... In presenting my results, I have purposefully shown equity curves from mean reversion strategies that go through periods of stellar performance as well as periods so bad that they would send most traders broke. Rather than cherry pick the good performance, I want to demonstrate what I think is of utmost importance in this type of trading, namely that the nature of mean reversion for any financial time series is constantly changing. At times this dynamism can...

This series of posts is inspired by several chapters from Ernie Chan's highly recommended book Algorithmic Trading. The book follows Ernie's first contribution, Quantitative Trading, and focuses on testing and implementing a number of strategies that exploit measurable market inefficiencies. I'm a big fan of Ernie's work and have used his material as inspiration for a great deal of my own research. My earlier posts about accounting for randomness (here and here) were inspired by the first chapter of Algorithmic Trading. Ernie works in MATLAB, but I'll be using R and Zorro. Ernie cites Daniel Kahneman's interesting example of mean reversion in the world around us: the Sports Illustrated jinx, namely that "an athlete whose picture appears on the cover of the magazine is doomed to perform poorly the following season" (Kahneman, 2011). Performance can be thought of as being randomly distributed around a mean, so exceptionally good performance one year (resulting in the appearance on the cover of Sports Illustrated) is likely to be followed by performances that are closer to the average. Mean reversion also exists in, or can be constructed from, financial time series...

Important preface: This post is in no way intended to showcase a particular trading strategy. It is purely to share and demonstrate the use of the framework I've put together to speed the research and development process for a particular type of trading strategy. Comments and critiques regarding the framework and the methodology used are most welcome. Backtest results presented are for illustrating the methodology and describing the outputs only. That done, on to the interesting stuff My last two posts (Part 1 here and Part 2 here) explored applying the k-means clustering algorithm for unsupervised discovery of candlestick patterns. The results were interesting enough (to me at least) to justify further research in this domain, but nothing presented thus far would be of much use in a standalone trading system. There are many possible directions in which this research could go. Some ideas that could be worth pursuing include: Providing the clustering algorithm with other data, such as trend or volatility information; Extending the search to include two- and three-day patterns; Varying the number of clusters; Searching across markets and asset...

In the first part of this article, I described a procedure for empirically testing whether a trading strategy has predictive power by comparing its performance to the distribution of the performance of a large number of random strategies with similar trade distributions. In this post, I will present the results of the simple example described by the code in the previous post in order to illustrate how susceptible trading strategies are to the vagaries of randomness. I will also illustrate by way of example my thought process when it comes to deciding whether to include a particular component in my live portfolio or discard it. I tested one particular trading system on a number of markets separately in both directions. I picked out three instances where the out of sample performance was good as candidates for live trading. The markets, trade directions and profit factors obtained from the out of sample backtest are as follows: USD/CAD - Short - Profit Factor = 1.79 GBP/USD - Long - Profit Factor = 1.20 GBP/JPY - Long - Profit Factor = 1.31 Next, I estimated the performance of...

Picture this: A developer has coded up a brilliant strategy, taking great care not to over-optimize. There is no look-ahead bias and the developer has accounted for data-mining bias. The out of sample backtest looks great. Is it time to go live? I would've said yes, until I read Ernie Chan's Algorithmic Trading and realised that I hadn't adequately accounted for randomness. Whenever we compute a performance metric from a backtest, we face the problem of a finite sample size. We can't know the true value of the performance metric, and the value we computed may or may not be representative of this true value. We may have been simply fooled by randomness into thinking we had a profitable strategy. Put another way, was the strategy's performance simply due to being in the market at the right time? There are a number of empirical methods that can be used to address this issue. Chan describes three in his book mentioned above, and there are probably others. I am going to implement the approach described by Lo, Mamaysky and Wang (2000), who simulated...