Machine learning can balance risks involved in bitcoin trading. Arshak Navruzyan, founder of Startup.ML, has been applying machine learning to quantitative finance problems. Bitcoin allows relatively small scale investors access to exchanges IBTimes UK. In terms of the directional movement of bitcoin the currency, 2015 saw near 40% gains making it one of the best performing financial instruments out there. But often traders are seeking greater returns than that and don't necessarily want the directional exposure, but just want to capture bitcoin's volatility. This means trading bitcoin at a higher frequency, balancing transaction costs and execution risk – and this can be facilitated by machine learning. Arshak Navruzyan the founder of Startup.ML, who has been applying machine learning to quantitative finance problems, found that cryptocurrency is also interesting because it allows relatively small scale investors access to exchanges, where they can get full order book data and trade more cost effectively compared to going through a brokerage. Navruzyan said: "This is actually one of the exciting things about cryptocurrency; why a lot of our modelling work is happening in this area is because you do get access to exchanges even as a little guy." A key thing for alpha traders is the concept of transaction costs. Volatility and transaction costs kind of go hand in hand, and if your transaction costs are high then your prediction has to be accurate for your alpha strategy to work. Another key idea, associated with bitcoin, is low liquidity, which is kind of the flipside of volatility. The amount that changes hands on a given exchange on daily basis is not very much at all. On Coinbase's GDAX, for example, only about five million dollars worth gets traded on a daily basis. Regarding transaction costs, a lot of exchanges favour market-making strategies versus taker strategies (maker being someone that's adding orders to the book; taker being someone that is taking those orders from the book). As a maker you pay a lot less fees. Navruzyan said: "If you can make predictions for a maker strategy that's probably the easiest way for a new trader to try to get alpha generation happening on Bitcoin. Now maker strategies are inherently more complex because you are putting limit orders on the book. "So even though you have fewer fees, you have now introduced a significant amount of execution risk, the book will run away from you, as it were. You are trying to get within that spread, but the book at high velocity will go off in a completely different direction and your order just sits there." There are two places where machine learning can be used to gain alpha. One aspect of this is making a directional forecast for the instrument. So you decide what your hold time frame is going to be; it could be an hour it could be six hours, it could be five minutes. "You build a machine learning model to try and forecast the direction of the instrument. That allows you to take either a long or a short position in the instrument for some period of time that you have designated. "Another part, that we are doing lot of research on, is actually getting the trades executed, particularly when you have a market making strategy, which is great because the transaction costs are very low or non-existent. "We are researching areas where machine learning can actually overcome that execution risk. In other words while you are market-making, machine learning is assisting you in getting your orders executed," said Navruzyan. An explanation of how Navruzyan's execution risk machine learning system operates gets into some pretty deep proprietary waters. He said a lot of execution optimisation systems within traditional markets basically look at the order book pretty closely; they look at buy pressure, sell pressure and try to assess which way the liquidity flows are happening within the order book. "We are building an intelligent system; we are building an AI that does this," he said. Machine learning for Bitcoin trading. Bitcoin and other cryptocurrency markets are still a very recent development. Traditional traders have not yet fully exploited this new environment. This makes cryptocurrency markets a perfect application for machine learning trading strategies. In this short post, I will show you how to apply Algominr to create a Bitcoin strategy. Note that Algominr will not get access to your wallet, but you will rather trade through a broker of your choice. Setup. At the current stage of development, Algominr requires Metatrader 4 (a trading client) to trade its machine learning strategies. There are several brokers which offer the Metatrader 4 client platform (short: MT4) in combination with cryptocurrencies. Additionally, most of them offer paper trading accounts, so that you can test your strategies without risking any real money. The following list provides a selection of brokers that support MT4: There’s many more broker’s offering MT4 for crypto-trading. A more complete list can be found here. Go to one of these brokers and download and install MT4 before continuing with this tutorial. When starting MT4 for the first time, you will be asked wheter you want to create a demo or a live account. Choose demo account for now. This will create a virtual trading account that let’s you try your strategies without risking any real money (or bitcoin). That’s it for now in MT4. Next, please download and install the current version of Algominr. Now it’s time to connect MT4 and Algominr. Just follow this short Tutorial: Data Import. To import the bitcoin symbol into Algominr, add a new Instrument on the left hand side of the Algominr interface. Click on the button with the + sign. and select BTCUSD (or any of the other cryptocurrencies, for simplefx they are quite far down in the list) Click on import to import the BTCUSD symbol. Next we will want to create a strategy that trades Bitcoin. In the top left, you have a basic strategy created from a template: First let’s change these settings to be more suitable for bitcoin. Set the Strategy Name to BTCUSD_S1 and hit enter. Next, set the order size to 1and hit enter. This will make the strategy trade 1 Bitcoin per trading signal. Leave the rest of the settings as they are. Strategy Logic. Now switch to the logic tab where you can see the strategy logic. Our first bitcoin strategy will be very simple, as we’re going to use a random forest (a popular machine learning method) to predict wether the price moves up or down in the next 60 minutes. To do this, we will change the Lin reg node to a RForest node. Click on the circle item on the Lin Reg node. In the popup, click on the Predict category and choose RForest. Make sure to set the Num features parameter to 4, the threshold to 0.01, the shift parameter to 20 and activate the Balance train sample feature. This will predict the bitcoin price change 20 minutes into the future. When done, click add. Next, make sure that the Market B/S node, the Indicators node, as well as the Bar Price node, all use the BTCUSD instrument. (Click on the circle icon of each of the nodes and check the settings) Next we will need to train and test the strategy on historical data. So click the Train/Test button on the right hand side of the Strategy view. This will activate the Simulation tab, where you can see how well your strategy works on historical data. As you can see, with this very simple strategy and a little machine learning, we can create a profitable strategy with very little effort. You can now click Deploy to start trading the strategy with your MT4 demo account. Let me know if you have any comments or questions. Also check out these youtube videos to learn more about Algominr and what strategies you can create: admin. Let me know if you have questions or comments: algominr (at) gmail.com. You may also like. Create an Artificial Neural Network strategy. Let’s create a more sophisticated strategy now. We are going to use two artificial neural networks to predict the relationship between […] Algominr Setup. In this quick tutorial, we will see how we can quickly setup Algominr Alpha 1.2 (Donwload) Don’t have a broker that support […] Page unavailable. The information you're looking for cannot be found, it may be temporarily unavailable or permanently removed. Try refreshing the page, or returning to our homepage. If the problem continues, please let us know. Cookies. Over 10 million scientific documents at your fingertips. © 2017 Springer International Publishing AG. Part of Springer Nature.