In today’s era of big data, deep learning and artificial intelligence have formed the backbone for cryptocurrency portfolio optimization. Researchers have investigated various state of the art machine learning models to predict Bitcoin price and volatility. Machine learning models like recurrent neural network (RNN) and long short-term memory (LSTM) have been shown to perform better than traditional time series models in cryptocurrency price prediction. However, very few studies have applied sequence models with robust feature engineering to predict future pricing. In this study, we investigate a framework with a set of advanced machine learning forecasting methods with a fixed set of exogenous and endogenous factors to predict daily Bitcoin prices. We study and compare different approaches using the root mean squared error (RMSE). Experimental results show that the gated recurring unit (GRU) model with recurrent dropout performs better than popular existing models. We also show that simple trading strategies, when implemented with our proposed GRU model and with proper learning, can lead to financial gain.
Optimization methods are used to determine equilibria of investment in cryptocurrencies. The basic assumptions involve existence of a core group (the "wealthy") that fears the loss of substantial assets through government seizure. Speculators constitute another group that tends to introduce volatility and risk for the wealthy. The wealthy must divide their assets between the home currency and the cryptocurrency, while the government decides on the probability of seizing a fraction the assets of this group. Under the assumption that each group exhibits risk aversion through a utility function, we establish the existence and uniqueness of Nash equilibrium. Also examined is the more realistic optimization problem in which the government policy cannot be reversed, while the wealthy can adjust their allocation in reaction to the government's designation of probability. The methodology leads to an understanding the equilibrium market capitalization of cryptocurrencies.
Recently, the notion of cryptocurrencies has come to the fore of public interest. These assets that exist only in electronic form, with no underlying value, offer the owners some protection from tracking or seizure by government or creditors. We model these assets from the perspective of asset flow equations developed by Caginalp and Balenovich, and investigate their stability under various parameters, as classical finance methodology is inapplicable. By utilizing the concept of liquidity price and analyzing stability of the resulting system of ordinary differential equations, we obtain conditions under which the system is linearly stable. We find that trend-based motivations and additional liquidity arising from an uptrend are destabilizing forces, while anchoring through value assumed to be fairly recent price history tends to be stabilizing.
We introduce a new diffusion process Xt to describe asset prices within an economic bubble cycle. The main feature of the process, which differs from existing models, is the drift term where a mean-reversion is taken based on an exponential decay of the scaled price. Our study shows the scaling factor on Xt is crucial for modelling economic bubbles as it mitigates the dependence structure between the price and parameters in the model. We prove both the process and its first passage time are well-defined. An efficient calibration scheme, together with the probability density function for the process are given. Moreover, by employing the perturbation technique, we deduce the closed-form density for the downward first passage time, which therefore can be used in estimating the burst time of an economic bubble. The object of this study is to understand the asset price dynamics when a financial bubble is believed to form, and correspondingly provide estimates to the bubble crash time. Calibration examples on the US dot-com bubble and the 2007 Chinese stock market crash verify the effectiveness of the model itself. The example on BitCoin prediction confirms that we can provide meaningful estimate on the downward probability for asset prices.
Feb 6, 2018·Caginalp, C., & Caginalp, G. (2018). Opinion: Valuation, liquidity price, and stability of cryptocurrencies. Proceedings of the National Academy of Sciences, 115(6), 1131-1134
Cryptocurrencies are examined through the asset flow equations and experimental asset markets. Since tangible value of a typical cryptocurrency is non-existent, the theory suggests that price will gravitate toward liquidity value, i.e., the total amount of cash available for purchase of the asset divided by the number of units. Thus it is unlikely that cryptocurrencies in their current form will be stable in the absence of a mechanism of a link to value.
Marian Gidea, Daniel Goldsmith, Yuri Katz, Pablo Roldan · 5 authors
We analyze the time series of four major cryptocurrencies (Bitcoin, Ethereum, Litecoin, and Ripple) before the digital market crash at the end of 2017 - beginning 2018. We introduce a methodology that combines topological data analysis with a machine learning technique -- $k$-means clustering -- in order to automatically recognize the emerging chaotic regime in a complex system approaching a critical transition. We first test our methodology on the complex system dynamics of a Lorenz-type attractor, and then we apply it to the four major cryptocurrencies. We find early warning signals for critical transitions in the cryptocurrency markets, even though the relevant time series exhibit a highly erratic behavior.
We introduce blockchains and distributed ledgers and describe their potential applications to money and banking. The analysis compares public and private ledgers and outlines the suitability of various types of ledgers for different purposes. Furthermore, a few historical prototypes of blockchains and distributed ledgers are presented, and results of their hard forking are illustrated. Next, some potential applications of distributed ledgers to trading, clearing and settlement, payments, trade finance, etc. are outlined. Monetary circuits are argued to be natural applications for blockchains. Finally, the role of digital currencies in modern society is articulated and various forms of digital cash, such as central bank issued electronic cash, bank money, bitcoin and P2P money, are compared and contrasted. Keywords: blockchains, distributed ledgers, digital currencies, modern monetary circuit; credit creation banking; interconnected banking network.
Alessandra Cretarola, Gianna Figà‐Talamanca, Marco Patacca
In recent literature it is claimed that BitCoin price behaves more likely to a volatile stock asset than a currency and that changes in its price are influenced by sentiment about the BitCoin system itself; in Kristoufek [10] the author analyses transaction based as well as popularity based potential drivers of the BitCoin price finding positive evidence. Here, we endorse this finding and consider a bivariate model in continuous time to describe the price dynamics of one BitCoin as well as a second factor, affecting the price itself, which represents a sentiment indicator. We prove that the suggested model is arbitrage-free under a mild condition and, based on risk-neutral evaluation, we obtain a closed formula to approximate the price of European style derivatives on the BitCoin. By applying the same approximation technique to the joint likelihood of a discrete sample of the bivariate process, we are also able to fit the model to market data. This is done by using both the Volume and the number of Google searches as possible proxies for the sentiment factor. Further, the performance of the pricing formula is assessed on a sample of market option prices obtained by the website deribit.com.