Information transfer between time series is calculated using the asymmetric information-theoretic measure known as transfer entropy. Geweke’s autoregressive formulation of Granger causality is used to compute linear transfer entropy, and Schreiber’s general, non-parametric, information-theoretic formulation is used to quantify nonlinear transfer entropy. We first validate these measures against synthetic data. Then we apply these measures to detect statistical causality between social sentiment changes and cryptocurrency returns. We validate results by performing permutation tests by shuffling the time series, and calculate the Z -score. We also investigate different approaches for partitioning in non-parametric density estimation which can improve the significance. Using these techniques on sentiment and price data over a 48-month period to August 2018, for four major cryptocurrencies, namely bitcoin (BTC), ripple (XRP), litecoin (LTC) and ethereum (ETH), we detect significant information transfer, on hourly timescales, with greater net information transfer from sentiment to price for XRP and LTC, and instead from price to sentiment for BTC and ETH. We report the scale of nonlinear statistical causality to be an order of magnitude larger than the linear case.
Chongyang Bai, Tommy E. White, Linda Xiao, V. S. Subrahmanian · 5 authors
We study the problem of predicting whether the price of the 21 most popular cryptocurrencies (according to coinmarketcap.com) will go up or down on day d, using data up to day d-1. Our C2P2 algorithm is the first algorithm to consider the fact that the price of a cryptocurrency c might depend not only on historical prices, sentiments, global stock indices, but also on the prices and predicted prices of other cryptocurrencies. C2P2 therefore does not predict cryptocurrency prices one coin at a time --- rather it uses similarity metrics in conjunction with collective classification to compare multiple cryptocurrency features to jointly predict the cryptocurrency prices for all 21 coins considered. We show that our C2P2 algorithm beats out a recent competing 2017 paper by margins varying from 5.1-83% and another Bitcoin-specific prediction paper from 2018 by 16%. In both cases, C2P2 is the winner on all cryptocurrencies considered. Moreover, we experimentally show that the use of similarity metrics within our C2P2 algorithm leads to a direct improvement for 20 out of 21 cryptocurrencies ranging from 0.4% to 17.8%. Without the similarity component, C2P2 still beats competitors on 20 out of 21 cryptocurrencies considered. We show that all these results are statistically significant via a Student's t-test with p<1e-5. Check our demo at https://www.cs.dartmouth.edu/dsail/demos/c2p2
The research is done to forecast the Bitcoin prices, the study considered Bitcoin prices. The data has been collected in an hourly basis from 1st July 2017 to 1st July 2018. The data is of high frequency. The forecast has been made for a period of 12 months from 31st July 2018 to 31st July 2019. The forecasted data has two different periods, one to calculate the error and the other to have an idea of the future price changes. The study uses Autoregressive Integrated Moving Average(ARIMA) and Seasonal Decomposition method for forecasting the Bitcoin prices. This article also helps the investors to have an idea about the future prices of Bitcoin. The forecasted prices also act as a factor for investor decision making, based on the forecast further choices can be made based on the Bitcoin price changes and invest accordingly. The results of this paper have has sown that, between the two models used, ARIMA has resulted to be the best model compared to the seasonal decomposition model as, the Mean Absolute Error, Mean Absolute Percentage Error and Root Mean Square Error is lower in ARIMA forecasting model, which satisfies the objective of the paper and the best model is selected.
Ismael Estalayo, Javier Del Ser, Eneko Osaba, Miren Nekane Bilbao · 7 authors
Nowadays the widespread adoption of cryptocurrencies (also referred to as Altcoins) has universalized the access of the society to trading opportunities in alternative markets, thereby laying a rich substrate for the development of new applications and services aimed at easing the management of personal investment portfolios. When selecting how much to invest and in which asset it is often the case that multiple criteria conflict with each other within a single decision making process, which calls for efficient means to optimally balance such contradicting objectives. In this paper we report initial findings around the combination of Deep Learning (DL) models and Multi-Objective Evolutionary Algorithms (MOEAs) for allocating cryptocurrency portfolios. Technical rationale and details are given on the design of a stacked DL recurrent neural network, and how its predictive power can be exploited for yielding accurate ex ante estimates of the return and risk of the portfolio. These two objectives are complemented by a measure of the diversity of the investment. Results are presented and discussed with real cryptocurrency data, showcasing the potential of our technical approach to produce near-optimal portfolios by balancing the aforementioned objectives. Our study stimulates further research towards incorporating other factors in the design of predictive portfolios, such as the confidence of the DL model output.
In recent years, cryptocurrencies have become more and more popular around the world, and they are being accepted and used by more countries. Cryptocurrencies are decentralized, and they form an emerging market that is different from stocks. At present, there is already much work around the stock price prediction using news articles, but there are few papers on the cryptocurrency market. In this paper, we aim to research the effects of news articles on bitcoin prices. We extract features from news articles with both commonly used text feature extraction algorithms (e.g., N-Gram and TF-IDF) and SentiGraph, which is a novel text representation method we propose. SentiGraph takes advantages of sentiment analysis and transforms a news article into a graph. Compared with previous feature extraction methods, our experiment results show that this new approach is superior on the prediction accuracy, which also demonstrates the impacts of news articles on the bitcoin price.
Jim Kyung-Soo Liew, Richard Li, Tamás Budavári, Avinash Sharma
In this work we examine the largest 100 cryptocurrency return series ranging from 2015 to early 2018. We concentrate our analysis on daily returns and find several interesting stylized facts. First, principal components analysis reveals a complex return generating process. As we examine our data in the most recent year, we find that surprisingly more than one principal component appears to explain the cross-sectional variation in returns. Second, similar to hedge fund returns, cryptocurrency returns suffer from the “beta-in-the-tails” hidden risk. Third, we find that predicting cryptocurrency movements with machine learning and artificial intelligence algorithms is marginally attractive with variation in predictability power per cryptocurrency. Fourth, lower volatile cryptocurrencies are slightly more predictable than more volatile ones. Fifth, evidence exists that efficacy of distinct information sets varies across machine learning algorithms, showing that predictability may be much more complex given a set of machine learning algorithms. Finally, short-term predictability is very tenuous, which suggests that near-term cryptocurrency markets are semi-strong form efficient and therefore, day trading cryptocurrencies may be very challenging. Keywords: cryptocurrency, blockchain, machine learning, bitcoin, beta-in-the-tails, risks
We investigate the extent to which Bitcoin price fluctuations are associated with investors’ sentiment disagreement. We employ three textual sentiment analysis techniques: 1) a Python library offered by the Computational Linguistics and Psycholinguistics Research Center; 2) Loughran and McDonald’s (2011) dictionary; and 3) semantic orientation by the point-wise mutual information method. The results show that investors’ attention and sentiment disagreement induce extremely high volatility and jumps in Bitcoin prices. These findings complement existing studies on how investors’ sentiment manifests in asset prices.
The Bitcoin protocol and its underlying cryptocurrency have started to shape the way we view digital currency, and opened up a large list of new and interesting challenges. Amongst them, we focus on the question of how is the price of digital currencies affected, which is a natural question especially when considering the price rollercoaster we witnessed for bitcoin in 2017-2018. We work under the hypothesis that price is affected by the web footprint of influential people, we refer to them as crypto-influencers.
Khalid Abouloula, Ali Ou-yassine, Salah-ddine Krit
In automatic trading, the interfaces to use in fulfilment are predefined to launch the platform for trade, which provides computers with the ability to make decisions and learn without explicit programming where all monitors are automated. The main goal of this chapter is to set a trading algorithm for a quick action in the market of smart money, using data science in the analysis of the integration, the distributed ledger technology to securities network and managing the trading account of a token ecosystem, which they are the basics of the crypto-currencies to enhance momentum trading strategies during the time frame of automated broker, and the trading with a large portfolio strategy in the market that needs big data.
With the introduction of Bitcoin in the year 2008 as the first practical decentralized cryptocurrency, the interest in cryptocurrencies and their underlying technology, Blockchain, has skyrocketed. Their promise of security, anonymity, and lack of a central controlling authority make them ideal for users who value their privacy. Academic research on machine learning, Blockchain technology, and their intersection have increased significantly in recent years. Specifically, one of the interest areas for researchers is the possibility of predicting the future prices of these cryptocurrencies using supervised machine learning techniques. In this thesis, we investigate their ability to make one day ahead price prediction of several popular cryptocurrencies using five widely used time-series prediction models. These models are designed by optimizing model parameters, such as activation functions, before settling on the final models presented in this thesis. Finally, we report the performance of each time-series prediction model measured by its mean squared error and accuracy in price movement direction prediction.
Abid Inamdar, Aarti Bhagtani, Suraj K. Bhatt, Pooja M. Shetty
This paper cross validates thesis given by few authors on the impact of social media on cryptocurrency prices. Initially, the focus is on the Bitcoin, later on, a similar model can be used for other cryptocurrencies. Sentiment scores of tweets and news feeds are considered along with historical prices and its volume to predict prices. Experimental results show that there is not much impact of sentiment scores unless these scores are not biased to one particular class.
In this study, we use random forest to predict several cryptocurrencies' prices by using part of factors in Alpha101 [1] to represent features from the history of cryptocurrencies' market data on Binance and Bitfinex. The result shows our strategy with some factors from Alpha101 is effective in cryptocurrency trading.
Juan Plazuelo Pascual, Carlos Tardon Rubio, Juan Toro Cebada, Angel Hernando Veciana
This document analyzes price discovery in cryptocurrency markets by comparing centralized and decentralized exchanges, as well as spot and futures markets. The study focuses first on Ethereum (ETH) and then applies a similar approach to Bitcoin (BTC). Chapter 1 outlines the theoretical framework, emphasizing the structural differences between centralized exchanges and decentralized finance mechanisms, especially Automated Market Makers (AMMs). It also explains how to construct an order book from a liquidity pool in a decentralized setting for comparison with centralized exchanges. Chapter 2 describes the methodological tools used: Hasbrouck's Information Share, Gonzalo and Granger's Permanent-Transitory decomposition, and the Hayashi-Yoshida estimator. These are applied to explore lead-lag dynamics, cointegration, and price discovery across market types. Chapter 3 presents the empirical analysis. For ETH, it compares price dynamics on Binance and Uniswap v2 over a one-year period, focusing on five key events in 2024. For BTC, it analyzes the relationship between spot and futures prices on the CME. The study estimates lead-lag effects and cointegration in both cases. Results show that centralized markets typically lead in ETH price discovery. In futures markets, while they tend to lead overall, high-volatility periods produce mixed outcomes. The findings have key implications for traders and institutions regarding liquidity, arbitrage, and market efficiency. Various metrics are used to benchmark the performance of modified AMMs and to understand the interaction between decentralized and centralized structures.
Sosyal medya, insanları alış veriş alışkanlıklarından yatırım kararlarına kadar birçok ticari niyetleri üzerinde yüksek etki düzeyi olduğu güncel birçok çalışmada araştırılmaya başlanmıştır ve bu ilişki ortaya konmuştur. Bu ilişki üzerine inşa edilerek geliştirilen güncel analiz yöntemleri yatırım araçlarının gelecek değerlerini tahmin ederek yatırım kararları almada bir destek mekanizması olarak kullanılması çok cazip bir konudur. Bu sebeple bu ilişki yatırımcı ve analistlerden akademisyenlere kadar güncel bir ilgi konusu olmuştur. Bu çalışmanın amacı da sosyal medya ile yatırım kararları arasındaki ilişkiyi metinsel ve finansal analiz aracılığı ile görmeye çalışmaktır. Bu çalışmada Twitter üzerinden metin madenciliği ile veri çekilmiş ve sentiment(duygu) analizi ile yorumların olumlu ya da olumsuz olma durumu incelenmiştir. Sentiment analizinden elde edilen sayısal değerler ile güncel ve küresel bir yatırım aracı olan Bitcoin fiyatları arasındaki ilişkinin varlığını sorgulamak adına Granger Nedensellik analizi gibi finansal analizler kullanılmıştır.
Dhyanendra Jain, Ashu Jain, Amit Pandey, Jogender Kumar
Abstract Bitcoin is one of the crypto currencies and is most unpredictable currencies. In the world of crypto currencies, the value of a coin can unpredictably upgrade or degrade. In this study, the model has been trained to predict the value of Bitcoin in USD at any given time stamp. For this prediction, three algorithms of machine learning - Linear Regression (LR), Support Vector Regression (SVR) and Neural Network Regression (NNR) have been used. The model is trained using the collected dataset. After the collection of data set, we first applied SVR algorithm, then we used LR and then NNR to calculate the error compared to the actual value. Root mean squared error (RMSE) is used as the predictive measure. Out of the three algorithms, LR was found out to be more accurate for predicting the value of bitcoin.
Recent studies have found that the log-volatility of asset returns exhibit roughness. This study investigates roughness or the anti-persistence of Bitcoin volatility. Using the multifractal detrended fluctuation analysis, we obtain the generalized Hurst exponent of the log-volatility increments and find that the generalized Hurst exponent is less than $1/2$, which indicates log-volatility increments that are rough. Furthermore, we find that the generalized Hurst exponent is not constant. This observation indicates that the log-volatility has multifractal property. Using shuffled time series of the log-volatility increments, we infer that the source of multifractality partly comes from the distributional property.
Long-term prediction of multivariate time series is still an important but challenging problem. The key to solve this problem is to capture the spatial correlations at the same time, the spatio-temporal relationships at different times and the long-term dependence of the temporal relationships between different series. Attention-based recurrent neural networks (RNN) can effectively represent the dynamic spatio-temporal relationships between exogenous series and target series, but it only performs well in one-step time prediction and short-term time prediction. In this paper, inspired by human attention mechanism including the dual-stage two-phase (DSTP) model and the influence mechanism of target information and non-target information, we propose DSTP-based RNN (DSTP-RNN) and DSTP-RNN-2 respectively for long-term time series prediction. Specifically, we first propose the DSTP-based structure to enhance the spatial correlations between exogenous series. The first phase produces violent but decentralized response weight, while the second phase leads to stationary and concentrated response weight. Secondly, we employ multiple attentions on target series to boost the long-term dependence. Finally, we study the performance of deep spatial attention mechanism and provide experiment and interpretation. Our methods outperform nine baseline methods on four datasets in the fields of energy, finance, environment and medicine, respectively.
Bitcoin is considered the most valuable currency in the world. Besides being highly valuable, its value has also experienced a steep increase, from around 1 dollar in 2010 to around 18000 in 2017. Then, in recent years, it has attracted considerable attention in a diverse set of fields, including economics and computer science. The former mainly focuses on studying how it affects the market, determining reasons behinds its price fluctuations, and predicting its future prices. The latter mainly focuses on its vulnerabilities, scalability, and other techno-crypto-economic issues. Here, we aim at revealing the usefulness of traditional autoregressive integrative moving average (ARIMA) model in predicting the future value of bitcoin by analyzing the price time series in a 3-years-long time period. On the one hand, our empirical studies reveal that this simple scheme is efficient in sub-periods in which the behavior of the time-series is almost unchanged, especially when it is used for short-term prediction, e.g. 1-day. On the other hand, when we try to train the ARIMA model to a 3-years-long period, during which the bitcoin price has experienced different behaviors, or when we try to use it for a long-term prediction, we observe that it introduces large prediction errors. Especially, the ARIMA model is unable to capture the sharp fluctuations in the price, e.g. the volatility at the end of 2017. Then, it calls for more features to be extracted and used along with the price for a more accurate prediction of the price. We have further investigated the bitcoin price prediction using an ARIMA model, trained over a large dataset, and a limited test window of the bitcoin price, with length $w$, as inputs. Our study sheds lights on the interaction of the prediction accuracy, choice of ($p,q,d$), and window size $w$.
Karunya Rathan, Somarouthu Venkat Sai, T Sai Lakshmi Manikanta
Crypto-currency such as Bitcoin is more popular these days among investors. In the proposed work, it is studied to forecast the Bitcoin price precisely considering different parameters that influence the Bitcoin price. This study first handles, it is identified the price trend on day by day changes in the Bitcoin price while it gives knowledge about Bitcoin price trends. The dataset till current date is taken with open, high, low and close price details of Bitcoin value. Exploiting the dataset machine learning module is introduced for prediction of price values. The aim of this work is to derive the accuracy of Bitcoin prediction using different machine learning algorithm and compare their accuracy. Experiment results are compared for decision tree and regression model.
The goal of this paper is to explore the relationship between momentum effects and liquidity in cryptocurrency markets. Portfolios based on momentum-liquidity bivariate sorts are formed and rebalanced on a varying number of cryptocurrencies through time. We find a strong momentum effect in the most liquid cryptocurrencies, which supports the theories of investor herding behavior. Moreover, we propose two profitable long-only strategies: the illiquid losers and liquid winners, which exhibit improved risk adjusted performance over the market capitalization weighted portfolio.
With the popularity of Bitcoin, a cryptocurrency market emerged. However, because of insufficient supervision, the market attracts scams, for example, pump and dump (P&D) scheme, a famous fraudulent behavior in stock markets, has been found rampant in the market. To help deal with this issue, as a preliminary study, this paper proposes an improved apriori algorithm to detect user groups which may involve in P&D schemes. The validity of the algorithm is verified by using the leaked transaction history of Mt. Gox Bitcoin exchange. Furthermore, by exploring some of the detected user groups, many abnormal trading behaviors in the exchange found. These findings provide new insights into the behavior of users in the cryptocurrency market, thus leading to meaningful implications for policymakers, investors, and managers dealing with the cryptocurrency market.
Project based learning is the methodology in which projects drive knowledge and is used in dedicated subjects without negotiating the coverage of the required technical material. This paper discusses the scheme and delivery of project based learning in computer science engineering as major project which adopts undergraduate creativities and emphasizes on real-world, open-ended projects. These projects foster a wide range of abilities, not only those related to content knowledge or technical skills, but also practical skills. The goal for this innovative undergrad project is to show how a trained machine model can predict the price of a cryptocurrency if we give the right amount of data and computational power. It displays a graph with the predicted values. The most popular technology is the kind of technological solution that could help mankind predict future events. With vast amount of data being generated and recorded on a daily basis, we have finally come close to an era where predictions can be accurate and be generated based on concrete factual data. Furthermore, with the rise of the crypto digital era more heads have turned towards the digital market for investments. This gives us the opportunity to create a model capable of predicting crypto currencies primarily Bitcoin. This can be accomplished by using a series of machine learning techniques and methodologies.