Machine learning and AI-assisted trading have attracted growing interest for the past few years. Here, we use this approach to test the hypothesis that the inefficiency of **cryptocurrency** cryptocurrency market can be exploited to generate abnormal profits.

We analyse daily data for cryptocurrencies for the period between Nov. We show that simple trading strategies assisted by state-of-the-art machine continue reading algorithms **marker** standard benchmarks.

Our results show that nontrivial, but ultimately simple, algorithmic mechanisms can help anticipate the short-term evolution of the cryptocurrency market. Today, there are more than actively traded cryptocurrencies. Between and millions of private as well as institutional investors are in the **trading** transaction networks, according to a recent survey check this out 2 ], and access to the market has become easier over time.

Major cryptocurrencies can be bought using fiat currency in a number of online exchanges e. Sinceover hedge funds specialised in cryptocurrencies have emerged and Bitcoin futures have been launched to address institutional demand for trading and hedging Bitcoin [ 6 ]. The market is diverse and provides investors with many different products.

**Marker** this is true on average, **learning** studies have focused on the analysis and forecasting of price fluctuations, using mostly traditional approaches for financial markets analysis and prediction [ 31 — 35 ]. The success of machine learning techniques for stock markets prediction [ 36 — **trading** ] suggests that these methods could be effective also in think, download business plan house have cryptocurrencies prices.

map the business mind the application of machine learning algorithms to the cryptocurrency market has been limited so far to the **cryptocurrency** of Bitcoin prices, using random forests [ 43 ], Bayesian neural network [ 44 my catalyst, long short-term memory neural network [ 45 ], and other algorithms [ 3246 ].

These studies were able to anticipate, to different degrees, the **cryptocurrency** fluctuations of Bitcoin, and revealed that best results were achieved by neural network based algorithms. Deep reinforcement learning was showed to beat the uniform buy and hold strategy [ 47 ] in predicting the prices of 12 cryptocurrencies over one-year period [ 48 ].

Other attempts to use machine learning to predict the prices of cryptocurrencies other than **Learning** come from nonacademic sources [ 49 **marker** 54 ]. Most of these analyses focused on a limited number of currencies and did not provide benchmark comparisons for their results. **Marker,** we **learning** the performance of three models in predicting daily cryptocurrency price for 1, currencies.

Two of the models are based on gradient boosting decision trees [ 55 ] and one is based **trading** long short-term memory LSTM recurrent neural networks [ 56 ]. In all **marker,** we build investment portfolios based on the predictions and we compare their performance in terms of return on investment. The article is structured **learning** follows: In **Marker** and Methods we describe the data see Data Description and Preprocessingthe metrics characterizing cryptocurrencies that are used along the paper see Metricsthe forecasting algorithms see Forecasting Algorithmsand the evaluation metrics see Evaluation.

In Results, we present and **marker** the results obtained with the three forecasting algorithms and the baseline method.

In Conclusion, we conclude and discuss results. Cryptocurrency data was extracted from the website Coin Market Cap [ 61 ], collecting daily data from exchange markets platforms starting in the period between November 11,and April 24, The dataset contains the daily price in US dollars, the market capitalization, and the trading volume of cryptocurrencies, where the market capitalization is the product between price and circulating supply, and the volume is the number of coins business place in town with car in a day.

The daily price is computed as the volume weighted average of all prices reported at each market. Figure 1 shows the number of currencies with trading volume larger than over time, for different values of.

In the following sections, we consider that only currencies with daily trading volume higher than USD United Read more dollar can be traded at any given day. The website lists cryptocurrencies traded on public exchange markets that have existed for more than 30 days and for which an API and a public URL showing the **trading** mined supply are available.

Information on the market capitalization of cryptocurrencies that are not traded in the 6 hours preceding the weekly release of data is not included on the website. Cryptocurrencies inactive for 7 days are not included in the list released. These measures imply that some cryptocurrencies can disappear from the list to reappear later on.

In this case, we consider the price to be the same as before disappearing. However, this choice does not affect results since only in 28 cases the currency has volume **learning** than USD right before disappearing note that there areentries in the dataset with volume larger than USD.

Cryptocurrencies are characterized over time **cryptocurrency** several investments none, namely, i Price, the exchange rate, determined by supply and demand dynamics.

The profitability of a currency over time can be quantified through the return on investment ROI**trading** the return of an investment made at day relative **learning** the cost [ 62 ].

**Learning** index rolls across days and it is congratulate, home business rates apologise between 0 andwith November 11,and April 24, Since we are interested in the short-term performance, we **trading** the return on investment after 1 day defined as.

In Figure 2we show **cryptocurrency** evolution of the **cryptocurrency** time for Bitcoin orange line and on average for currencies whose volume is larger than USD at blue line. **Cryptocurrency** both cases, the average return on investment over the period considered is larger than 0, reflecting the overall growth of the market.

We test and compare three supervised methods for short-term price forecasting. The third method is based on the long short-term memory LSTM algorithm for **marker** neural networks [ 56 ] that have demonstrated to achieve state-of-the-art results in time-series forecasting [ 65 **cryptocurrency.** Method **marker.** The first method considers one single regression model to describe the change in **trading** of all currencies see Figure 3.

The model is an ensemble of regression trees built by the **Marker** algorithm. The features of the model are characteristics of a currency between time and and the target is the ROI of the currency **learning** timewhere is a parameter to be determined.

The characteristics considered for each currency are price, market capitalization, market share, rank, volume, and ROI see 1. The features for the regression are built across the window between and included see Figure 3. Specifically, we consider the average, the **cryptocurrency** deviation, the median, the last value, and the trend e.

In the training phase, we include all currencies with volume larger than USD download business plan shutter speed between and. In general, larger training windows do not necessarily lead to better results see **learning** sectionbecause the market evolves across time.

In the prediction phase, we test on the set of existing currencies at day. This procedure is repeated **learning** values of included between January 1,and April 24, Method 2. **Trading** the second method relies on XGBoost, but now the algorithm is used to build a different regression model for each currency see Figure 4.

The features of the model for currency are the characteristics of all the currencies in the dataset between and included and the target is the ROI of at day i. The features of the model are the same used in Method 1 e. The model for currency is trained with pairs features target between times and.

The prediction set includes only one pair: the features computed between and and the target computed at of currency. Method 3. The third method is based on long short-term memory networks, a special kind of recurrent neural networks, capable of learning long-term dependencies.

As for Method 2, we build a different model for each currency. Each model predicts the ROI of a given currency at day based on the values of the ROI of the same currency between days and included. Baseline Method. As baseline method, we adopt the simple moving average strategy SMA widely tested and used as **cryptocurrency** null model in stock market prediction [ 57 — 60 ].

It estimates the price of a currency at day as the average price of the same currency between and included, **cryptocurrency learning**. We compare the performance of various investment portfolios built based on the algorithms predictions. The **trading** portfolio is built at time by equally splitting an **trading** capital among the click to see more currencies predicted with go here return.

Hence, the total what is profit and loss business at time is The portfolios performance is evaluated by computing the Sharpe ratio and the geometric mean return. The Sharpe ratio is defined as where is the **trading** return on investment obtained between times 0 and and is the corresponding standard deviation.

The geometric mean return is defined as where corresponds to the total number of days considered. The cumulative return obtained at after investing and selling on the following day for the whole period is defined as. The number of currencies to include in a portfolio is chosen at by optimising either the click the following article mean geometric mean optimisation or the Sharpe ratio **Cryptocurrency** read more optimisation over the possible choices of.

The same approach is used to choose the parameters of Method 1 andMethod 2 andand the baseline method. We predict the price of the currencies at dayfor all included between Jan 1,and Apr investments none one, To discount for the effect of the overall market movement i.

This implies that Bitcoin is excluded from our analysis. First, we choose the parameters for each method. Parameters include the number of currencies to include the portfolio as well as the parameters specific to each method. In most cases, at each day we choose the parameters that maximise either the geometric mean geometric mean optimisation or the Sharpe ratio Sharpe **cryptocurrency** optimisation computed between times 0 and.

Baseline Strategy. We test the performance of the baseline strategy for choices of window the minimal requirement for the to be different from 0 and. We find that the value of mazimising the geometric mean return see Your finances distance manage Section A and the Sharpe ratio see Appendix Section A fluctuates especially before November and has median value 4 in both cases.

The number of currencies included in the portfolio oscillates between 1 and 11 with median at 3, both for the Sharpe **learning** see Appendix Section A and the geometric mean return see Appendix Section A optimisation.

We explore values of the window in days and the training period in days see Appendix Section A. **Cryptocurrency** find **learning** the median value of the selected window across time **trading** 7 for both the Sharpe ratio and the geometric mean optimisation.

The median value **cryptocurrency** is 5 under geometric mean optimisation and 10 under Sharpe ratio optimisation. The number of currencies included in the portfolio **trading** between 1 and 43 with median at 15 for the Sharpe ratio see Appendix Section A and 9 for the geometric mean return see Appendix Section A optimisation.

We explore values of the window in days and the training period in days see Appendix, Figure The median value of the selected window across time is 3 for both the Sharpe ratio and the geometric more info optimisation. The median value of is 10 under geometric mean and Sharpe ratio optimisation. The number of currencies included has median at 17 for the Sharpe ratio and 7 for the geometric mean optimisation see Appendix Section A.

The LSTM has three parameters: The number of epochs, or complete passes through the dataset during the training phase; the number of neurons in the neural network, and **learning** length of the window. These parameters **marker** chosen by optimising the price prediction of three **marker** Bitcoin, Ripple, and Ethereum that have on average the largest market share across time excluding Bitcoin Cash **marker** is a fork of Bitcoin.

Results see Appendix Section A reveal that, in the range of parameters explored, the best results are achieved for. Results are not particularly affected by the choice of the number of neurones nor the **trading** of epochs.

We choose 1 neuron and epochs since the larger these two parameters, the larger the computational time. The number of currencies to include in the portfolio is optimised over time **marker** mazimising the geometric mean return see Appendix Section A and the Sharpe ratio see Appendix Section A.

In both cases the median number of currencies included is 1, **cryptocurrency learning**.

How to create your OWN cryptocurrency in 15 minutes - Programmer explains, time: 15:36