Cryptocurrencies differ significantly from traditional financial assets because they rely on new technologies and can experience large fluctuations in value, often experiencing sudden upswings or bubbles.
This paper applies machine learning techniques to the cryptocurrency market and examines several trading strategies. Regression and classification random forests (RFs) are employed in this study with data obtained from exchange trading information, lag returns, lagged volatility proxies, and Parkinson range volatility estimators as input.
Market Capitalization
Market capitalization of a cryptocurrency refers to its total current price multiplied by its outstanding shares or units, and serves as an important metric for investors when assessing potential returns from investing in digital currencies.
There is an increasing number of cryptocurrencies with significant market capitalization, both centralized and decentralized; Bitcoin being the most prominent among them and experiencing its price skyrocket recently.
Cryptocurrency prices fluctuate quickly and are highly unpredictable; however, their market trend tends to be upward. As more people become acquainted with cryptocurrencies like Bitcoin, their adoption will likely increase as people gain knowledge of them and come to rely on them as stores of value. Decentralization makes Bitcoin resistant to corruption and fraud while simultaneously serving as an invaluable store of value.
Market Capitation Ratio (MCR)
Cryptocurrencies are an emerging asset class utilizing cryptography for security. They tend to be free from government manipulation and control, making them ideal for trading on exchanges, holding as investments or paying debts.
Bitcoin, with a market cap of over $1 trillion, remains the premier cryptocurrency, but other cryptocurrencies have gained in popularity too; some may even go beyond Bitcoin in terms of value.
Ripple offers banks a cross-border payment solution utilizing blockchain technology for international payments, with fast settlement times to reduce the costs of high-value international transactions that are otherwise slow and expensive. Their digital currency, XRP, was created specifically to assist with these transactions – though concerns exist that Ripple could use its control of total supply to manipulate market pricing, potentially devaluing it further and undermining its utility – though any change must go through a consensus mechanism between holders, which might prove challenging.
Price Index
Cryptocurrency prices are notoriously unstable and can rise or fall depending on supply and demand. Unlike stock markets, cryptocurrency values depend solely on public sentiment analysis – an outcome which can change at any moment.
Bitcoin is the world’s most famous cryptocurrency, using a blockchain ledger to transfer value and make payments. Other cryptocurrencies, including Litecoin, Ethereum and Ripple employ similar technologies for transactions.
Bitcoin’s network is decentralized and cannot be controlled by one entity, its blockchain a shared record which updates constantly allowing wallets to calculate their spendable balance and new transactions to verify as spending those funds; furthermore it also ensures integrity and chronological order for transactions.
Volume
Recently, cryptocurrency research has received increased scrutiny in both finance and economics fields. Cryptocurrencies are characterized by relatively high market capitalizations and trading volumes; their volatility is greater than traditional securities like stocks, bonds, or foreign exchange; as such many researchers are exploring their dynamics using nonlinear approaches such as trajectory modelling and structural breaks.
These methods can be utilized to examine the directional spillover of risk across cryptocurrency markets, which could assist investors in designing investment portfolios that maximize returns while protecting themselves against nonidiosyncratic risks. Furthermore, knowledge of tail spillover between distinct crypto markets could aid policymakers in improving and maintaining financial stability.
We analyze the flow of shocks through a network of 27 pairwise links between five cryptocurrencies and three volatility indices, using 27 pairwise links in pairs as pairswise links between themselves. On average, we observe negative directional spillover between them, meaning they tend to transmit more shocks than receive them; net pairwise connectedness values shift more strongly toward positive axes for all markets except BTC and ETH.
