David Alaminos, M. BelĂŠn Salas-CompĂĄs, Manuel Ă. FernĂĄndez-GĂĄmez
In recent years, Bitcoin has garnered attention as a digital currency, prompting increasing debate regarding its effects on traditional financial markets, particularly the US dollar. This study investigates the relationship between Bitcoin and the US dollar, especially in the contexts of speculative attacks, where investors attempt to devalue a currency, and short squeezes, where rapid price rises force short sellers to quickly buy back assets to avoid further losses. The study employs a novel hybrid model combining an autoregressive moving average, Generalized Autoregressive Conditional Heteroskedasticity, and Wavelet Neural Networks techniques with neural networks approaches. The results suggest that significant trading activity in Bitcoin/US dollar, particularly during speculative attacks and short squeezes, can substantially impact the US dollar/EUR market, increasing price volatility as traders adjust their strategies. These adjustments, along with risk management strategies, drive higher trading volumes and further volatility. Our findings demonstrate that our novel hybrid model combined with Quantum Recurrent Neural Networks provides the most accurate predictions, offering valuable insights to inform trading strategies in both Bitcoin/US dollar and US dollar/EUR markets. This study has important implications for policymakers and market participants, emphasising the need to understand the relationship between Bitcoin and the US dollar for financial stability and effective policy formulation. It also highlights the necessity of advanced modeling techniques to accurately predict cryptocurrency market behavior.
Masoud Omidvari Abarghouie, Sasan H. Alizadeh, Ahmad Khademzadeh
The rise of cryptocurrencies as a major economic factor has drawn interest from both individual investors and regulators. This has led researchers to explore new ways to predict cryptocurrency volatility. This research proposes a new approach for more accurately predicting the conditional variance of cryptocurrencies while previous research did not investigate cross-correlation among cryptocurrency mean and volatility landscapes. This research precisely uses a method to select the most relevant features based on the cross-correlation between price, returns, and volatility. Experiments on eight cryptocurrencies that have the largest market capacity from 2018 to 2024 show that this approach is effective. By considering stronger cross-correlation when choosing the data used for volatility prediction using LSTM, the research substantially reduces the error of prediction. The findings of this research can be used to predict the volatility of other cryptocurrencies and the stock markets.
With the gradual development and integration of artificial intelligence into various industries, there is also a great range of integration in the financial industry. Therefore, this article focuses on the trend prediction model and financial risk management problems of deep reinforcement learning (DRL), one of the largest branches of artificial intelligence, in the cryptocurrency market. In addition, in the experimental part of this paper, the artificial intelligence machine learning Long short-term memory network (LSTM) model is used to make effective time series prediction and analysis on the relevant data of the cryptocurrency market, so as to make a large-scale analysis to improve the accuracy of market trend prediction and the effectiveness of risk management. In addition, in this experiment, technology-related indicators, emotional states of financial market customers and other content related to large language models are combined. While optimizing investment strategy by using deep reinforcement learning algorithm, machine learning prediction model is also used to capture the time dependence of financial market. The experimental results also show that the predicted results are consistent with the actual value. Therefore, the model has high practical application value in predicting the time series price trend of cryptocurrency in the financial market and indicates that the integrated DRL model framework can further optimize and manage the price and trading strategy of the financial market. Future research should focus on improving the LSTM model and incorporating more features to improve prediction accuracy and adapt to market changes.
Adi Prasetyo, Nurdin Nurdin, Hafizh Al Kautsar Aidilof
Cryptocurrency has emerged as a prominent digital asset over the past decade, but its high price volatility presents significant challenges for investors. This study evaluates and compares the effectiveness of the Triple Exponential Smoothing (TES) and Autoregressive Integrated Moving Average (ARIMA) methods in forecasting the prices of five major cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Binance Coin (BNB), Solana (SOL), and Ripple (XRP). TES models trends and seasonality in time series data, while ARIMA captures autoregressive patterns and moving averages. The dataset is split into 80% for training and 20% for testing, with performance evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). TES outperforms ARIMA in predicting Bitcoin and Binance Coin, achieving MAPE values of 10.38% and 13.81%, and RMSE values of 3,985.55 and 41.28, respectively. However, ARIMA shows better performance for Ethereum, Solana, and Ripple, with MAPE ranging from 8.78% to 32.84% and RMSE between 0.08 and 204.59. Notably, Ethereum has the lowest MAPE at 8.78%, while Ripple exhibits the smallest RMSE at 0.08. These findings suggest that TES is more suitable for cryptocurrencies with relatively stable price patterns, while ARIMA is better adapted to forecasting highly volatile assets. This research underscores the importance of selecting forecasting models based on the specific characteristics of each cryptocurrency
This study investigates public sentiment about popular cryptocurrencies listed on crypto exchanges in Turkey, using comments shared on social media platforms and online forums. The research seeks to enhance the existing body of knowledge by overcoming the shortcomings of sentiment analysis studies focused on Turkish texts. Data collected from social media and online forums were examined with sentiment analysis techniques. A total of 607,592 comments were analyzed, of which 89,986 were classified as negative, 72,655 as positive, and 444,951 as neutral. For binary classification, 89,986 negative and 72,655 positive examples were selected and machine-learning models were trained and tested on 162,641 examples. The study's methodology includes an in-depth examination of sentiment analysis results obtained using machine learning classifiers. The findings show how various cryptocurrencies are perceived on different social media platforms. For instance, BTC (Bitcoin) is generally perceived negatively on Investing.com and Telegram, while ETH (Ethereum) generally displays more negative views. These results help investors understand their perceptions and market expectations towards cryptocurrencies. This study deepens the role of social media sentiment analysis in cryptocurrency markets, contributing to the development of new methods and approaches for future research.
Popular methods to value Bitcoin include the stock-to-flow model, Metcalfeâs Law, technical analysis, and sentiment-related measures. Within this paper, I test whether such models and variables are predictive of Bitcoinâs returns. I find that the stock-to-flow model predictions and Metcalfeâs Law help to explain Bitcoinâs returns in-sample but have limited to no ability to predict Bitcoinâs returns out-of-sample. In contrast, Bitcoin market sentiment and technical analysis measures are generally unrelated to Bitcoinâs returns in-sample and are poor predictors of Bitcoinâs returns out-of-sample. Despite the poor performance of Bitcoin return predictors within out-of-sample regressions, I demonstrate that a very successful out-of-sample Bitcoin tactical allocation or âmarket timingâ strategy is formed via blending out-of-sample univariate model predictions. This OOS-blended model trading strategy, which algorithmically allocates between Bitcoin and cash (USD), significantly outperforms buying-and-holding or âHODLâing Bitcoin, boosting CAPM alpha by almost 1300 basis points while also increasing portfolio Sharpe Ratio and Sortino Ratio and dramatically reducing portfolio maximum drawdown relative to buying-and-holding Bitcoin.
This study proposes an Automatic Cryptocurrency Trading System using Deep Reinforcement Learning (DRL). Six popular cryptocurrencies were used: Bitcoin, Ethereum, BinanceCoin, DogeCoin, Cardano, and WAVES. Development of the trading system started with building three timeseries models â Temporal Convolutional Neural Network (TCNN), Long Short-Term Memory Network (LSTM), and Gated Recurrent Unit Network (GRU) â to predict future prices. Then, cryptocurrency sentiment data was scraped using the Alternative.me API. Data on historical prices, predicted future prices, cryptocurrency sentiment index, technical indicators, and trading account information was fed as input states to three DRL Agents â Deep Q Network (DQN), Advantage Actor Critic (A2C), and Recurrent Proximal Policy Optimization (RPPO) â which were trained using a custom-developed trading environment. Each agent was given $1000 initial capital for all six cryptocurrencies to trade using three possible actions â Buy, Sell and Hold â and were back-tested on one year of unseen data. Our DQN model had the highest overall return on investment (ROI) of $740, an average 12.3% ROI across all six cryptocurrencies, with an ROI of 63.98% achieved for BinanceCoin. However, A2C and RPPO both had negative ROI.
This paper delves into analyzing and predicting cryptocurrency prices, focusing on Bitcoin. It employs displaced moving average (DMA) and long short-term memory (LSTM) techniques. By leveraging these methods, we aim to provide valuable insights for those navigating the volatile world of cryptocurrency investments. After extracting it using Python within a Jupyter Notebook environment, a dataset sourced from Yahoo Finance is utilized. The analysis incorporates 50 DMA and 200 DMA to enhance understanding of bitcoin market dynamics and offers insights into the predictive capabilities of moving averages. Subsequently, the study applies LSTM, a recurrent neural network combining forget and output gates, to enhance memory and assess attributes critical for accurate price forecasting. The study systematically assesses model performance using important metrics like MSE (Mean Squared Error), R-squared (R2) factor, and the RMSE (Root Mean Squared Error) for understanding accuracy and reliability. For comparison, the traditional regression method is also analyzed for Bitcoin price forecasting, revealing the outperformance of LSTM over regression.
Predicting cryptocurrency price trends remains a major challenge due to the volatility and complexity of digital asset markets. Artificial intelligence (AI) has emerged as a powerful tool to address this problem. This study proposes a multisource fusion framework that integrates quantitative financial indicators, such as historical prices and technical indicators, with qualitative sentiment signals derived from X (formerly Twitter). Sentiment analysis is performed using Financial Bidirectional Encoder Representations from Transformers (FinBERT), a domain-specific BERT-based model optimized for financial text, while sequential dependencies are captured through a Bidirectional Long Short-Term Memory (BiLSTM) network. Experimental results on a large-scale Bitcoin dataset demonstrate that the proposed approach substantially outperforms single-source models, achieving an accuracy of approximately 96.8\%. The findings underscore the importance of incorporating real-time social sentiment alongside traditional indicators, thereby enhancing predictive accuracy and supporting more informed investment decisions.
Bitcoin, launched in 2009 as the pioneer cryptocurrency, has caught the eye of investors worldwide due to its nature and remarkable growth. Recent studies indicate that elements, like announcements, news sentiments, government regulations, and overall market sentiments significantly influence the trajectory of bitcoin price. This work presents a comprehensive analysis to provide deeper insights into the relationship between user sentiments expressed as tweets and bitcoin prices (daily price changes). As a significant contribution, the authors propose multiple approaches to performing the non-trivial task of integrating tweet sentiment with bitcoin price data. The chapter also presents the incorporation of inherent lag in the expression of sentiments and their impact on price change by demonstrating lagged sentiment analysis. The work employs state-of-the-art machine learning and deep learning models for analyzing the data both as classification and regression tasks to uncover hidden patterns.
Recently, quantitative trading techniques applied in financial research have become increasingly sought after. Quantitative trading refers to the use of statistics and computer techniques to aid trading decisions. Bitcoin has attracted a large number of investors to invest in it due to its decentralised nature, anonymity, and total number of 21 million pieces. This paper wishes to profit from investing in Bitcoin. This paper predicts the logarithmic return of Bitcoin based on the Informer model. Because of the high volatility of Bitcoin, this paper shortens the prediction period of the Informer model from the traditional 24 days to 1 day. In addition, this paper introduces the technique of migration learning, where models trained on five tech company datasets are migrated to Bitcoin's dataset for training tests. This compensates for the small Bitcoin dataset to some extent. In this paper, MSE, MAE, and R-squared were used as the evaluation metrics with MSE of 0.5678, MAE of 0.5087, and R-squared of 0.232313938. The results show that the Informer model's short-term forecasting ability is validated. The value of this paper is to provide Bitcoin investors with a possible method to aid trading decisions.
Abstract This study provides a comprehensive review of machine learning (ML) applications in the fields of business and finance. First, it introduces the most commonly used ML techniques and explores their diverse applications in marketing, stock analysis, demand forecasting, and energy marketing. In particular, this review critically analyzes over 100 articles and reveals a strong inclination toward deep learning techniques, such as deep neural, convolutional neural, and recurrent neural networks, which have garnered immense popularity in financial contexts owing to their remarkable performance. This review shows that ML techniques, particularly deep learning, demonstrate substantial potential for enhancing business decision-making processes and achieving more accurate and efficient predictions of financial outcomes. In particular, ML techniques exhibit promising research prospects in cryptocurrencies, financial crime detection, and marketing, underscoring the extensive opportunities in these areas. However, some limitations regarding ML applications in the business and finance domains remain, including issues related to linguistic information processes, interpretability, data quality, generalization, and the oversights related to social networks and causal relationships. Thus, addressing these challenges is a promising avenue for future research.
The prime aim of the research is to forecast the future value of bitcoin that is commonly known as pioneer of the Cryptocurrency market by constructing hybrid structure over the time series. In this perspective, two separate hybrid structures were created by using Artificial Neural Network (ANN) together with Genetic Algorithm (GA) and Particle Swarm Optimization Algorithm (PSO). By using the hybrid structures created, both the network model and the hyper parameters in the network structure, together with the time intervals of the daily closing prices and how many data should be taken retrospectively, were optimized. Employing the created GA-ANN (DCP1) and PSO-ANN (DCP2) hybrid structures and the 721-day Bitcoin series, the goal of accurately predicting the values that Bitcoin will receive has been achieved. According to the comparative results obtained in line with the stated objectives and targets, it has been determined that the structure obtained with the DCP1 hybrid model has a success rate of 99% and 97.54% in training and validation, respectively. It should also, be underlined that the DCP1 model showed 47% better results than the DCP2 hybrid model. With the proposed hybrid structure, the network parameters and network model that should be used in the ANN network structure are optimized in order to obtain more efficient results in cryptocurrency price forecasting, while optimizing which input data should be used in terms of frequency and closing price to be chosen.
The utilization of machine learning techniques for predicting cryptocurrency prices has become increasingly prominent. Researchers have investigated a variety of methods, including recurrent neural networks, deep learning architectures, Bayesian regression, k-nearest neighbors, and support vector machines, to forecast prices for cryptocurrencies such as Bitcoin, Ethereum, Dogecoin, and Litecoin, etcetera. This research draws from existing studies on price prediction across different domains, including the predictability of sales, fluctuations of sale prices, gold price forecasting, and silver price predictions. The focus has been on exploiting high-dimensional features and time-series analysis while comparing various statistical and machine learning models. Models have also incorporated factors such as market liquidity and exchange dynamics. Although current literature acknowledges the potential of these methods in predicting cryptocurrency, gold and silver, there is a noted gap in applying these techniques to a wider range of cryptocurrencies. Crypto-Visionary will integrate a variety of machine learning and statistical techniques to forecast prices for cryptocurrencies, gold and silver, considering factors like market trends, trading networks, and visual attributes. Additionally, the importance of feature engineering and sample dimension manipulation is emphasized to improve the accuracy and reliability of predictions. As the cryptocurrency market evolves, there is a growing need for further research to develop robust models capable of forecasting prices for a diverse set of cryptocurrencies, thereby advancing the field.
Cryptocurrency is a digital or virtual currency that uses a decentralized system through cryptography for secure financial transaction and record keeping. This process is widely known as mining, where the decentralized nature of the system works without central issuance. One of the objectives is to the end that the spread of the influence of institutions and organizations should be up to the users/investors with enhanced authority. In India, this has been under deployment and substantial deliberation in the relevance and importance it has come to assume in the lives of people. This is largely due to the fact that availability has increased, and it also would need high utilization of processor by things like mining. The recent past has increasingly seen popularity and importance to which cryptocurrencies hold relevance. In fact, this was manifest in the massive growth of rapid advances and that which had led many global businesses to acknowledge the importance of using this technology to gain access to myriad quantitative benefits electronically. The concept of rice forecasting has been very pivotal in different industries, like in cryptocurrency and stock prices. It greatly challenges the current financial market since indeed, traders have had the dilemma of selling their cryptocurrencies or buying them.
Predicting Bitcoin prices is crucial because they reflect trends in the overall cryptocurrency market. Owing to the market's short history and high price volatility, previous research has focused on the factors influencing Bitcoin price fluctuations. Although previous studies used sentiment analysis or diversified input features, this study's novelty lies in its utilization of data classified into more than five major categories. Moreover, the use of data spanning more than 2,000 days adds novelty to this study. With this extensive dataset, the authors aimed to predict Bitcoin prices across various timeframes using time series analysis. The authors incorporated a broad spectrum of inputs, including technical indicators, sentiment analysis from social media, news sources, and Google Trends. In addition, this study integrated macroeconomic indicators, on-chain Bitcoin transaction details, and traditional financial asset data. The primary objective was to evaluate extensive machine learning and deep learning frameworks for time series prediction, determine optimal window sizes, and enhance Bitcoin price prediction accuracy by leveraging diverse input features. Consequently, employing the bidirectional long short-term memory (Bi-LSTM) yielded significant results even without excluding the COVID-19 outbreak as a black swan outlier. Specifically, using a window size of 3, Bi-LSTM achieved a root mean squared error of 0.01824, mean absolute error of 0.01213, mean absolute percentage error of 2.97%, and an R-squared value of 0.98791. Additionally, to ascertain the importance of input features, gradient importance was examined to identify which variables specifically influenced prediction results. Ablation test was also conducted to validate the effectiveness and validity of input features. The proposed methodology provides a varied examination of the factors influencing price formation, helping investors make informed decisions regarding Bitcoin-related investments, and enabling policymakers to legislate considering these factors.
This paper explores the volatility spillover effects between the cryptocurrency market and the Pakistan Stock Exchange (PSX). Utilising data from January 1, 2019, to April 5, 2024, sourced from Investing and Yahoo Finance, the study employs the Multivariate Generalized Autoregressive Conditional Heteroskedasticity (MGARCH) BEKK model to assess the dynamic interactions between these markets. Stationarity tests confirmed the non-stationarity of time series data at their levels, which became stationary after first differencing, ensuring robust econometric analysis. The results indicate significant volatility spillovers from major cryptocurrencies, such as Bitcoin and Ethereum, to the PSX, highlighting a solid interconnectedness between these markets. This suggests that digital asset volatility significantly influences traditional financial systems. The study concludes that integrating cryptocurrencies into global financial markets introduces risks and opportunities for investors and policymakers. The findings underscore the need for market participants to account for these volatility interactions in their risk management strategies. Additionally, policymakers must consider these interlinkages to maintain financial stability. This research contributes to the literature on financial market volatility by emphasising the importance of understanding the impact of emerging digital currencies on traditional stock markets.
Abstract This study proposes a quote-driven predictive automated market maker (AMM) platform with on-chain custody and settlement functions, alongside off-chain predictive reinforcement learning capabilities, to improve the liquidity provision of real-world AMMs. The proposed architecture augments Uniswap V3, a cryptocurrency AMM protocol, by using a novel market equilibrium pricing to reduce divergence and slippage losses. Furthermore, the proposed architecture involves a predictive AMM capability, for which a deep hybrid long short-term memory (LSTM) and Q-learning reinforcement learning framework is used. It seeks to improve market efficiency through obtaining more accurate forecasts of liquidity concentration ranges, where liquidity starts moving to expected concentration ranges prior to asset price movement; thus, liquidity utilization is improved. The augmented protocol framework is expected to have practical real-world implications through (1) reducing divergence loss for liquidity providers; (2) reducing slippage for crypto-asset traders; and (3) improving capital efficiency for liquidity provision for the AMM protocol. The proposed architecture is empirically benchmarked against the well-established Uniswap V3 AMM architecture. The preliminary findings indicate that the novel AMM framework offers enhanced capital efficiency, reduced divergence loss, and diminished slippage, which could potentially address several of the challenges inherent to AMMs.