Blockchain Papers

Navid Parvini, Mahsa Abdollahi, Sattar Seifollahi, Davood Ahmadian

No abstract is available for this record.

Marco Ortu, Nicola Uras, Claudio Conversano, Silvia Bartolucci · 5 authors

No abstract is available for this record.

Nafiz Sadman, Md Manjurul Ahsan, Abdur Rahman, Zahed Siddique · 5 authors

Decentralized Finance (DeFi) is an emerging and revolutionizing field with notable uncertainties of reliability to be used on a mass scale. On the other hand, Artificial Intelligence (AI) has proved to be a crucial helping tool in numerous domains. In this study, we present a systematic review of the utility of AI in DeFi in terms of impact, reliability, and security and conduct exhaustive analysis. The review was motivated by an in-depth investigation of recently published literature that prioritized AI and DeFi in their research. This research, like many prior studies, examined the articles in terms of impact, reliability, and security. In addition, a new relevance score is introduced to better comprehend the quality of the content. According to investigation, the combination of AI and DeFi is one of the trending research topics that lacks adequate interpretations of black-box methodologies. Furthermore, it was discovered that one of the primary issues in DeFi is security, and numerous technologies, including blockchain technology and machine learning approaches, have been used to minimize such challenges. We hope that the gap addressed throughout this review will give insights to future researchers and practitioners, ultimately leading to new research opportunities in AI to bridge the gap of trust between peers and make the integration of DeFi more agile in the near future.

Shaad Iqbal Ansari, H Y Vani

In this article forecasting of daily closing price series of Bitcoin, Ripple, Dash, Litecoin and Ethereum crypto currencies, using data on prices (open, low, high), market capital and volumes using prior days is focused. The value conduct of cryptographic forms of money remains to a great extent neglected, giving new chances to scientists and business analysts to feature the likenesses and contrasts with standard monetary costs. Hence the paper is focused on this area. he results are compared with various benchmarks. Predictions are done using statistical techniques and machine learning algorithms. A simple linear regression (SLR) model that uses only a single-variable sequence of closing prices for forecasting, and a multiple linear regression (MLR) model that uses a multivariate sequence of prices and quantities at the same time. The simple linear regression (SLR) model for univariate serial forecasting uses only closing prices. Mean Absolute Percentage Error (MAPE) and relative Root Mean Square Error (relative RMSE) performance measures are considered. The accuracy achieved by the ARIMA model on our dataset is the highest, followed by Multivariable Linear Regression and LSTM.

Eric Edgari, Jocelyn Thiojaya, Nunung Nurul Qomariyah

Bitcoin have become safe-haven for people who want to invest during COVID-19 with its volatile price. Numerous factors can affect the price but recently the most popular one was due to an Elon Musk tweet. We decided to investigate our questions. Do tweets regarding Bitcoin affect its price? Can we predict Bitcoin price by analysing sentiments from twitter? For our research, we decided to analyze the impact of twitter sentiments on Bitcoin price during the COVID-19 pandemic. Using VADER sentiment analysis, we attempted to find out what is the current public sentiment regarding Bitcoin. Coupling tweet sentiment with the Bitcoin price, we pursue making a predictive model to forecast whether Bitcoin price will rise or fall. We also compare whether having twitter sentiment analysis in our model will have an advantage compared to not using. In the end, we found out that twitter sentiment analysis have an impact to Bitcoin price. We hope that our research can help people during this financial stress period.

Ehsan Sadeghi Pour, Hossein Jafari, Ali Lashgari, Elaheh Rabiee · 5 authors

In this paper we present a price prediction for Bitcoin prices. The methodology used is a hybrid artificial neural network model of Long Short-Term Memory and Bayesian Optimization. This is a complex model with a high prediction power, which to our knowledge has not been applied to prediction of cryptocurrency prices to date. Following Charandabi and Kamyar (2021), we elaborate on previous methods used for prediction of cryptocurrency prices and build on their methodology. We conclude with detailed graphs and tables of optimization results.

G NIRMALA, Santosh Mathan, K KARTHICK, D AKASHRAJA

This project is implemented to predict the Bitcoin price accurately taking into consideration various parameters that affects the Bitcoin value. Bitcoins are put away in an advanced wallet which is essentially similar to a virtual financial balance. it is important to anticipate the estimation of Bitcoin so right venture choices can be made. The cost of Bitcoin doesn’t rely upon the business occasions or mediating government not at all like securities exchange. Most measurable procedures pursue the worldview of deciding a specific probabilistic model that best portrays watched information among a class of related models. Likewise, most AI systems are intended to discover models that best fit information. By gathering information from different reference papers and applying in real time. Each and every project has its own set of methodologies of bitcoin price prediction. Machine learning models can likely give us the insight we need to learn about the future of Crypto currency. It will not tell us the future but it might tell us the general trend and direction to expect the prices to move.

Ricardo Leon-Ayala, Noe Vicente-Rosas, Nayely Quispe-Quispe, Luis Mesa-Salinas · 7 authors

No abstract is available for this record.

Haoran Lyu

In recent years, the expansion of the cryptocurrency market has received significant attention among investors, studies of cryptocurrency price predictions have been conducted in various fields. With the enhancement of machine learning algorithms and increased computational capabilities, machine learning has proved one of the most efficient cryptocurrency prediction methods. However, most studies focused on single digital currency prediction or small-scale algorithm comparison for multiple currencies. This study aims to present a comparative performance of large-scale selected Machine Learning algorithms for cryptocurrency forecasting. Specifically, this paper concentrates on forecasting time series data for a short-term trading period in ten cryptocurrencies (BTC, ETH, ADA, BNB, XRP, DOGE, LUNA, LINK, LTC, and BCH) with ten selected machine learning algorithms (Decision Tree, Linear Regression, Ridge Regression, Lasso Regression, Bayesian Regression, Random Forest, K-Nearest Neighbors, Neural Networks, Gradient Boosting, and Support Vector Machine). Our experiment results show that the Gradient Boosting with the mean square error criterion is superior in predicting most major cryptocurrencies by performing statistical analysis and data visualizations. Additionally, the Random Forest and Decision Tree model built by the Classification and Regression Tree algorithm also shows outstanding performance in certain currencies such as ETH, XRP, LUNA, and LTC. Thus, all three algorithms can help anticipate the short-term evolutions of the cryptocurrency market.

DIT, Pimpri, Pune, Indi, Ajinkya Auti, Dhananjay Patil, DIT, Pimpri, Pune, Indi · 10 authors

Bitcoin is one of the most valuable Crypto currency in the world with the prices as high as 68,078 United States Dollar (USD) in November of 2021. It made Bitcoin a very profitable market for investment but Bitcoin saw many ups and down as well. Prices of Bitcoin have highly fluctuated which make them very difficult to predict. Hence, this research aims to discover the most efficient and highest accuracy model to predict Bitcoin prices from various machine learning algorithms. By using 1-minute interval trading data on the Bitcoin exchange website named bitstamp some different regression models with Scikit- learn and Keras libraries had experimented. The dataset used contains minute by minute prices of Bitcoin of over 5 years and contains almost 3 Million entries. Since, the dataset used is a big data, evaluating the performance of algorithms over a large dataset will give accurate results.

Rebekka Buse, Konstantin Görgen, Melanie Schienle

We study the prediction of Value at Risk (VaR) for cryptocurrencies. In contrast to classic assets, returns of cryptocurrencies are often highly volatile and characterized by large fluctuations around single events. Analyzing a comprehensive set of 105 major cryptocurrencies, we show that Generalized Random Forests (GRF) (Athey, Tibshirani & Wager, 2019) adapted to quantile prediction have superior performance over other established methods such as quantile regression, GARCH-type and CAViaR models. This advantage is especially pronounced in unstable times and for classes of highly-volatile cryptocurrencies. Furthermore, we identify important predictors during such times and show their influence on forecasting over time. Moreover, a comprehensive simulation study also indicates that the GRF methodology is at least on par with existing methods in VaR predictions for standard types of financial returns and clearly superior in the cryptocurrency setup.

Zeinab Shahbazi, Yung-Cheol Byun

The popularity of cryptocurrency in recent years has gained a lot of attention among researchers and in academic working areas. The uncontrollable and untraceable nature of cryptocurrency offers a lot of attractions to the people in this domain. The nature of the financial market is non-linear and disordered, which makes the prediction of exchange rates a challenging and difficult task. Predicting the price of cryptocurrency is based on the previous price inflations in research. Various machine learning algorithms have been applied to predict the digital coins' exchange rate, but in this study, we present the exchange rate of cryptocurrency based on applying the machine learning XGBoost algorithm and blockchain framework for the security and transparency of the proposed system. In this system, data mining techniques are applied for qualified data analysis. The applied machine learning algorithm is XGBoost, which performs the highest prediction output, after accuracy measurement performance. The prediction process is designed by using various filters and coefficient weights. The cross-validation method was applied for the phase of training to improve the performance of the system.

Zhengkun Li

Value at risk and expected shortfall are increasingly popular tail risk measures in the financial risk management field. Both academia and financial institutions are working to improve tail risk forecasts in order to meet the requirements of the Basel Capital Accord; it states that one purpose of risk management and measuring risk accuracy is, since extreme movements cannot always be avoided, financial institutions can prepare for these extreme returns by capital allocation, and putting aside the appropriate amount of capital so as to avoid default in times of extreme price or index movements. Forecast combination has drawn much attention, as a combined forecast can outperform the individual forecasts under certain conditions. We propose two methodology, one is a semiparametric combination framework that can jointly produce combined value at risk and expected shortfall forecasts, another one is a parametric regression framework named as Quantile-ES regression that can produce combined expected shortfall forecasts. The favourability of the semiparametric combination framework has been presented via an empirical study - application in cryptocurrency markets with high-frequency data where the necessity of risk management application increases as the cryptocurrency market becomes more popular and mature. Additionally, the general framework of the parametric Quantile-ES regression has been presented via a simulation study, whereas it still need to be improved in the future. The contributions of this work include but are not limited to the enabling of the combination of expected shortfall forecasts and the application of risk management procedures in the cryptocurrency market with high-frequency data.

Jacques Fleischer, Gregor von Laszewski, Carlos Theran, Yohn Jairo Parra Bautista

In this paper we apply neural networks and Artificial Intelligence (AI) to historical records of high-risk cryptocurrency coins to train a prediction model that guesses their price. This paper's code contains Jupyter notebooks, one of which outputs a timeseries graph of any cryptocurrency price once a CSV file of the historical data is inputted into the program. Another Jupyter notebook trains an LSTM, or a long short-term memory model, to predict a cryptocurrency's closing price. The LSTM is fed the close price, which is the price that the currency has at the end of the day, so it can learn from those values. The notebook creates two sets: a training set and a test set to assess the accuracy of the results. The data is then normalized using manual min-max scaling so that the model does not experience any bias; this also enhances the performance of the model. Then, the model is trained using three layers -- an LSTM, dropout, and dense layer-minimizing the loss through 50 epochs of training; from this training, a recurrent neural network (RNN) is produced and fitted to the training set. Additionally, a graph of the loss over each epoch is produced, with the loss minimizing over time. Finally, the notebook plots a line graph of the actual currency price in red and the predicted price in blue. The process is then repeated for several more cryptocurrencies to compare prediction models. The parameters for the LSTM, such as number of epochs and batch size, are tweaked to try and minimize the root mean square error.

Ninuk Wiliani, Rizki Hesananda, Nidya Sari Rahmawati, Erdham Hestiadhi Prianggara

Predicting a currency Exchange rate and performing analysis is an action to try to determine the price valuation of a currency or other financial instrument traded on an exchange platform. Bitcoin is a consensus network that enables new payment systems and fully digital money. Bitcoin is the first decentralized peer to peer payment network that is fully controlled by its users without any central authority or intermediary. From the user's point of view, Bitcoin is like cash in the internet world. Bitcoin can also be viewed as the most prominent triple bookkeeping system in existence today. The change in Bitcoin's behavior against the US dollar is influenced by many factors. Basic or economic factors that may be affected include inflation rates and money supply. In this study, data was collected by obtaining all data through the API provided by binance.com and labeled with the specified attribute. The modeling is done by using the rapidminer application. The process begins by taking training data that has been provided previously. The next stage is the data testing process, all operators that have been previously determined are connected and tested using the Linear Regression operator. The purpose of testing this data is to predict stock prices from the testing data that has been made by the Split Data operator, which is 19% of the total data that has been prepared.

Uroosa Maqsood, Faheem Yar Khuhawar, Shahnawaz Talpur, Fawad Hassan Jaskani · 5 authors

The decentralization of cryptocurrency has decreased the level of central control, which has impacted international trade and ties. There is also an urgent need for a credible way of projecting the price of cryptocurrencies, which is currently unavailable. A novel method to predict cryptocurrency price is proposed in this paper, which makes use of deep learning techniques such as the recurrent neural network (RNN), gated recurrent unit (GRU), convolution 1D, and the long short-term memory (LSTM). This method considers a variety of factors such as market capitalization, volume, circulating supply, and maximum supply. It is more accurate at recognizing long-term relationships than the LSTM. Developed in Python, the proposed approach was tested on a range of real-world data sets. The findings demonstrate that the proposed method may be used to properly predict the price of cryptocurrencies.

Sandy Suardi, Atiqur Rahman Rasel, Bin Liu

No abstract is available for this record.

Zeyd Boukhers, Azeddine Bouabdallah, Cong Yang, Jan Jürjens

Since Bitcoin first appeared on the scene in 2009, cryptocurrencies have become a worldwide phenomenon as important decentralized financial assets. Their decentralized nature, however, leads to notable volatility against traditional fiat currencies, making the task of accurately forecasting the crypto-fiat exchange rate complex. In this study, we examine the various independent factors that affect the Bitcoin-Dollar exchange rate's volatility. To this end, we propose CoMForE, a multimodal AdaBoost-LSTM ensemble model, which not only utilizes historical trading data but also incorporates public sentiments from related tweets, public interest demonstrated by search volumes, and blockchain hash-rate data. Our developed model goes a step further by predicting fluctuations in the overall cryptocurrency value distribution, thus increasing its value for investment decision-making. We have subjected this method to extensive testing via comprehensive experiments, thereby validating the importance of multimodal combination over exclusive reliance on trading data. Further experiments show that our method significantly surpasses existing forecasting tools and methodologies, demonstrating a 19.29% improvement. This result underscores the influence of external independent factors on cryptocurrency volatility.

Dhanar Prayoga

Robo-advisor is one of the most prominent innovation in the wealth management industry, and its success in Indonesia has been evident in the case of Bibit. Therefore, wealth management companies need to employ Robo-Advisor to overcome their competition. This research aims to give recommendation on asset allocation method and asset class selection for Robo-Advisors in Indonesia using Sharpe Ratio Analysis. Then, the author will analyze the robo-advisor’s performance during equity market downturn. Finally, The Robo-Advisor’s actual performance will be tested in 2018, 2019, and 2020. The Sharpe ratio analysis result showed that Robo-Advisors seeking higher risk-adjusted return should choose mean-variance optimization over risk parity for asset allocation method, and the inclusion of gold and bitcoin in a portfolio of stock mutual fund and bond mutual fund increases the risk-adjusted return of the portfolio. The proposed robo-advisor’s portfolio protected investors from equity market downturn in 2011-2010 in 83,3% of the case. Finally, the proposed robo-advisor’s portfolio generated better return for the conservative, moderate and aggressive investor during 2018, 2019, and 2020 when compared to LQ45.

Kerolly Kedma Felix do Nascimento, Fábio Sandro dos Santos, Jader da Silva Jale, Sílvio Fernando Alves Xavier Júnior · 5 authors

No abstract is available for this record.

Jong‐Min Kim, Chanho Cho, Chulhee Jun

We employed linear and nonlinear error correction models (ECMs) to predict the log returns of Bitcoin (BTC). The linear ECM is the best model for predicting BTC compared to the neural network and autoregressive models in terms of RMSE, MAE, and MAPE. Using a linear ECM, we are able to understand how BTC is affected by other coins. In addition, we performed Granger-causality tests on fourteen cryptocurrencies.

Hatice Nazan Çağlar

Kaos Teorisi, doğrusal olmayan dinamik sistemlerin davranışlarını tanımlar ve ekonomi alanında pek çok verinin modellenmesinde kullanılır. Kaos teori, sistemin doğrusal olmayan ve deterministik bir süreç olduğu varsayımlarına dayanır. Doğrusal modeller, ekonometrik sistemleri karmaşıklıklarını ortaya çıkarmakta yetersiz kalmaktadır. Bu çalışmanın amacı, Bitcoin günlük fiyatlarının zamana bağlı doğrusal olmayan dinamik bir sistem tarafından üretilip üretilmediğini araştırmak ve sistemin uzun vadede geleceğe yönelik tahmin yeteneğini araştırmak ve bir tahminleme modeli oluşturmaktır. Birçok ekonomik veri serisinin kaotik davranış gösterdiği bilinmektedir. Bu çalışmada, Bitcoin fiyatlarının kaotik yapısı incelenmiş ve regresyon yöntemi kullanılarak tahmin modeli kurulmuştur. Diğer bir ifadeyle amaç, Bitcoin fiyatlarının getirilerinin kaotik bir davranış gösterip göstermediğini ortaya koyarak elde edilen gömme (embedding) boyutuna bağlı olarak regresyon yöntemini kullanarak tahmin modeli oluşturmaktır. Çalışmada, 2021 Şubat – 2021 Kasım döneminde günlük kapanış fiyatı ( $ ) veri olarak kullanılmıştır. (URL-1,2021)

Andrei-Dragoş Popescu

Investors now have a multitude of non-traditional assets to choose from, especially from the spectrum of alternative assets, such as financial digital assets. We start from the premise that there is a high risk associated with investing in financial digital assets, along with the opportunities presented from these emerging digital markets that evolve in a decentralized environment. We will be looking at the two major digital assets, specifically Bitcoin (BTC) and Ethereum (ETH), as per their dominance within the markets of crypto assets. This paper will focus on the evolution of financial digital assets and the impact on portfolio assessment that have allocations for BTC and ETH. In order to identify the value and potential of these financial digital assets, we will be addressing volatility and portfolio risks by means of a Vector Autoregression model on the returns of both, BTC and ETH.

Édouard Lansiaux, Noé Tchagaspanian, Joachim Forget

No abstract is available for this record.