In this paper, we discuss the method of Bayesian regression and its efficacy for predicting price variation of Bitcoin, a recently popularized virtual, cryptographic currency. Bayesian regression refers to utilizing empirical data as proxy to perform Bayesian inference. We utilize Bayesian regression for the so-called "latent source model". The Bayesian regression for "latent source model" was introduced and discussed by Chen, Nikolov and Shah (2013) and Bresler, Chen and Shah (2014) for the purpose of binary classification. They established theoretical as well as empirical efficacy of the method for the setting of binary classification. In this paper, instead we utilize it for predicting real-valued quantity, the price of Bitcoin. Based on this price prediction method, we devise a simple strategy for trading Bitcoin. The strategy is able to nearly double the investment in less than 60 day period when run against real data trace.
This paper analyzes correlations and causalities between Bitcoin market indicators and Twitter posts containing emotional signals on Bitcoin. Within a timeframe of 104 days (November 23rd 2013 - March 7th 2014), about 160,000 Twitter posts containing "bitcoin" and a positive, negative or uncertainty related term were collected and further analyzed. For instance, the terms "happy", "love", "fun", "good", "bad", "sad" and "unhappy" represent positive and negative emotional signals, while "hope", "fear" and "worry" are considered as indicators of uncertainty. The static (daily) Pearson correlation results show a significant positive correlation between emotional tweets and the close price, trading volume and intraday price spread of Bitcoin. However, a dynamic Granger causality analysis does not confirm a statistically significant effect of emotional Tweets on Bitcoin market values. To the contrary, the analyzed data shows that a higher Bitcoin trading volume Granger causes more signals of uncertainty within a 24 to 72-hour timeframe. This result leads to the interpretation that emotional sentiments rather mirror the market than that they make it predictable. Finally, the conclusion of this paper is that the microblogging platform Twitter is Bitcoin's virtual trading floor, emotionally reflecting its trading dynamics.
The Bitcoin has emerged as a fascinating phenomenon in the Financial markets. Without any central authority issuing the currency, the Bitcoin has been associated with controversy ever since its popularity, accompanied by increased public interest, reached high levels. Here, we contribute to the discussion by examining the potential drivers of Bitcoin prices, ranging from fundamental sources to speculative and technical ones, and we further study the potential influence of the Chinese market. The evolution of relationships is examined in both time and frequency domains utilizing the continuous wavelets framework, so that we not only comment on the development of the interconnections in time but also distinguish between short-term and long-term connections. We find that the Bitcoin forms a unique asset possessing properties of both a standard financial asset and a speculative one.
We use the GARCH group models to test whether margin trading can reduce the volatility of Chinese stock market,in both vertical and horizontal angles.The vertical analysis of GARCH model shows that,statistically speaking,the volatility of Chinese stock market significantly is reduced after margin trading has kicked in.Horizontal comparison reveals that compared to the Shanghai Composite Index,the SSE 50 Index,which contains a higher proportion of underlying stock,performs better in terms of reducing the volatility of the stock market with margin trading.Finally,based on results of our analysis,we suggest that credit should be conferred in a decentralized manner,that development and growth in financing and securities lending should proceed in a balanced fashion,and that a correct understanding of return matching risk should be cultivated among investors.
Optimization methods have had successful applications in business, economics, and finance. Nowadays the new theories of soft computing are used for these purposes. The applications in business, economics, and finance have specific features in comparison with others. The processes are focused on private corporate attempts at money making or decreasing expenses; therefore the details of applications, successful or not, are not published very often. The optimization methods help in decentralization of decision-making processes to be standardized, reproduced, and documented. The optimization plays very important roles especially in business because it helps to reduce costs that can lead to higher profits and to success in the competitive fight.
Abstract â The volatile nature of cryptocurrency markets has spurred interest in predictive models to aid investment and trading strategies. This study extends previous works by incorporating all available technical indicators, leveraging the TA library, and evaluating multiple deep learning architectures for Bitcoin price prediction. Using daily OHLC data for Bitcoin (BTC) sourced from Yahoo Finance, we implement Transformer-based Multi-Head Attention with GRU and LSTM layers, along with standalone LSTM and GRU models. These architectures are compared in terms of predictive accuracy to identify the most effective approach for capturing market dynamics. Our results provide a comprehensive analysis of model performance, highlighting the potential of advanced neural network architectures and technical indicators for improving cryptocurrency price prediction.
Abstractâ Cryptocurrency markets have experienced rapid growth, attracting attention from investors, traders, and researchers. Accurate price prediction is critical for effective risk management and investment strategies. This paper proposes a hybrid deep learning model that combines Transformer Encoder and Gated Recurrent Unit (GRU) architectures with technical indicators to predict cryptocurrency prices. The model uses daily OHLC data and selected technical indicators, achieving strong predictive performance on BTC-USD, ETH-USD, and BNB-USD. The results demonstrate that the model accurately captures price trends with low prediction errors, achieving RMSE and MAPE values of 2607.32 and 3.70% for BTC-USD, 205.86 and 6.02% for ETH-USD, and 21.45 and 4.09% for BNB-USD, respectively. These findings highlight the modelâs potential for developing adaptive trading strategies and advancing decision-making in cryptocurrency markets.