Alfonso Guarino, Luca Grilli, Domenico Santoro, Francesco Messina · 5 authors
Abstract Financial bubbles represent a severe problem for investors. In particular, the cryptocurrency market has witnessed the bursting of different bubbles in the last decade, which in turn have had spillovers on all the markets and real economies of countries. These kinds of markets and their unique characteristics are of great interest to researchers. Generally, investors and financial operators study market trends to understand when bubbles might occur using technical analysis tools. Such tools, which have been historically used, resulted in being precious allies at the basis of more advanced systems. In this regard, different autonomous, adaptive and automated trading agents have been introduced in the literature to study several kinds of markets. Among these, we can distinguish between agents with Zero/Minimal Intelligence (ZI/MI) and Computational Intelligence (CI) -based agents. The first ones typically trade on the market without resorting to complex learning strategies; the second ones usually use (deep) reinforcement learning mechanisms. However, these trading agents have never been tested on the cryptocurrencies market and related financial bubbles, which are still mostly overlooked in the literature. It is unclear how these agents can make profits/losses before, during, and after a bubble to adjust their strategy and avoid critical situations. This paper compares a broad set of trading agents (between ZI/MI and CI ones) and evaluates them with well-known financial indicators (e.g., volatility, returns Sharpe ratio , drawdown, Sortino and Omega ratio ). Among the experiment’s outcomes, ZI/MI agents were more explainable than CI ones. Based on the results obtained above, we introduce GGSMZ , a trading agent relying on a neuro-fuzzy mechanism. The neuro-fuzzy system is able to learn from the trades performed by the agents adopted in the previous stage. GGSMZ ’s performances overcome those of other tested agents. We argue that GGSMZ could be used by investors as a decision support tool.
This paper examines price discovery between bitcoin spot and futures using static measures, namely information share (IS), component share (CS), modified information share (MIS), information leadership share (ILS), impulse response, and a time-varying parameter vector autoregressive (TVP-VAR) model with stochastic volatility and Markov Chain Monte Carlo (MCMC) sampling algorithm. Our one-minute and daily datasets cover 16 months before and 16 months during the Covid-19 pandemic (November 2018 to June 2021). Our IS, CS, MIS and impulse response results indicate a stronger bitcoin spot leadership, whereas our ILS results point to a weaker bitcoin futures dominance, during the Covid-19 pandemic. We construe this, as far as microstructure noise is concerned, as meaning that the bitcoin price is discovered in the spot market, and its dominance appears to have strengthened during the pandemic. However, as far as ‘pure speed’ is concerned, price discovery takes place in the bitcoin futures market, and its leadership seems to have weakened during the Covid-19 pandemic. The results of the time-varying measure (TVP-VAR) imply that, before the pandemic, price discovery took place within bitcoin futures but, during the pandemic, price discovery leadership has changed course, to occur within bitcoin spot.
This paper investigates how to use deep learning methods to combine with traditional multi-factor models and construct a quantitative trading model based on an AutoEncoder algorithm (AE) to classify cryptocurrencies since 2009, so as to screen out ones with investment value and then construct an effective investment portfolio. The AE algorithm is capable of handling high-dimensional data and mining interfactor non-linearities. Our empirical results on cryptocurrencies show that the model outperforms single-type factors and benchmark in terms of Cumulative Returns and the Sharpe Ratio.
This study explores whether and to what extent cryptocurrency ecosystem network connectivity predicts Bitcoin returns across quantiles of the return distribution. The facets of cryptocurrency ecosystem network connectivity we consider include connectivity between the on- and off-chain segments of the Bitcoin market, the intensity and synchronization of social and traditional crypto-focused media activity, the intensity of network correlations between cryptocurrencies. We identify tail behaviour predictors employing a quantile regression approach. The results demonstrate the effectiveness of several connectivity measures in predicting both price spikes and downfalls, but in a different way before and during the COVID-19 outbreak.
The cryptocurrency market is generally accepted in the world, and its price has soared and plummeted sharply. Meanwhile, skewness is an index reflecting the rapid rise and fall of asset prices in a short period. Studying the relationship between the skewness of cryptocurrency and its returns can help risk evaders expect bad news and provide a reference for risk enthusiasts to make investment decisions. Therefore, through univariate combination analysis, this paper groups cryptocurrency according to the skewness of the previous month before buying and holding it in the next week. Moreover, the excess return series are calculated to make statistical tests on it. Then we construct a three-factor model of cryptocurrency and adjust the return series. To enhance the robustness of the conclusion, we also use other measures of skewness such as idiosyncratic skewness to conduct a univariate combination analysis. The results show that a positive correlation between cryptocurrency skewness and its returns exists, which can be used as a reference index of the returns.
Distributed ledger technology (DLT) is a disruptive technology with the potential to reengineer the entire trading cycle by alleviating inefficiencies such as time lags, multiple record keeping, human errors, and transparency common with the traditional trade cycle. This study evaluates the potential benefits of DLT in mitigating information asymmetry in trading relationships and how a DLT model can be deployed to revamp the trading process. We find that information friction results from differences in stakeholder preferences by identifying and categorizing information friction into 4 groups through a review of key studies in leading management journals. This finding aligns with conclusions reached in scientific research that the benefits of DLT prevail in markets with imperfect information. In addition, we illustrate the potential benefits of DLT in mitigating inefficiencies in trading relationships resulting from information asymmetry. The article concludes with a word of caution for potential users to take gradual steps of adoption to keep pace with changing technology so as not to become laggards.
This is the first study to examine the quantile connectedness for returns-volume and volatility-volume pairs for the three non-fungible tokens (THETA, Tezos, and Enjin Coin) using the quantile VAR approach. The results report the highest connectedness of volume with returns and volatility in the extreme upper quantile compared to other quantiles, implying the asymmetric connectedness. The spillover effect is observed from volume to returns and volatilities in extreme upper and lower market conditions, whereas opposite direction of spillovers is evident for the selected non-fungible tokens at median quantile. Our findings are useful for investors in predicting the returns and risk of NFTs using trading volume in the extreme market conditions.
Virtual currency has been greeted with an avalanche of attention these days. In this case, allocate investments into traditional assets and virtual currency properly seems very important. In this paper, we select gold and bitcoin as our research objects, and select a series of representative indicators in the financial field. After data preprocessing, XGBoost algorithm is used to sort the importance of indicators, thus eliminating some unimportant indicators. Next, LSTM is used to predict the price of gold and bitcoin respectively. Therefore, the portfolio can be built based on it. In reality, trades often come with transaction costs. So we improve the Mean-Variance model considering the transaction costs, so as to get the initial portfolio strategy. On this basis, taking investment potential into account, we propose Traffic Light Signal(TLS) model, and successfully increasing the gross profit rate from 11.582% to 13.614%. Finally, we prove our portfolio model earns the highest returns by comparing it to other traditional portfolio models in terms of metrics Cumulative Yield, Annual Yield, and Max Drawdown Ratio.
We investigate which factors contribute most to the liquidity of Bitcoin, using a diverse universe of candidate factors reflecting key developments in the crypto market and the global economy. The empirical analysis relies on three regularized linear regression methods, viz. LASSO, adaptive LASSO, and elastic net. We also apply a cross-fit partialing-out LASSO instrumental-variables regression model, as a supplementary approach to handle endogeneity. Findings reveal that trading volume and realized volatility of Bitcoin, cryptocurrency hacks, Ethereum liquidity, and public attention are the most common drivers of liquidity, irrespective of the penalized regression approach and liquidity proxy adopted. Our evidence confirms the paramountcy of cryptocurrency-specific factors over global economic and financial ones in influencing Bitcoin liquidity.
Over the past years, cryptocurrencies have drawn substantial attention from the media while attracting many investors. Since then, cryptocurrency prices have experienced high fluctuations. In this paper, we forecast the high-frequency 1 min volatility of four widely traded cryptocurrencies, i.e., Bitcoin, Ethereum, Litecoin, and Ripple, by modeling volatility to select the best model. We propose various generalized autoregressive conditional heteroscedasticity (GARCH) family models, including an sGARCH(1,1), GJR-GARCH(1,1), TGARCH(1,1), EGARCH(1,1), which we compare to a multivariate DCC-GARCH(1,1) model to forecast the intraday price volatility. We evaluate the results under the MSE and MAE loss functions. Statistical analyses demonstrate that the univariate GJR-GARCH model (1,1) shows a superior predictive accuracy at all horizons, followed closely by the TGARCH(1,1), which are the best models for modeling the volatility process on out-of-sample data and have more accurately indicated the asymmetric incidence of shocks in the cryptocurrency market. The study determines evidence of bidirectional shock transmission effects between the cryptocurrency pairs. Hence, the multivariate DCC-GARCH model can identify the cryptocurrency market’s cross-market volatility shocks and volatility transmissions. In addition, we introduce a comparison of the models using the improvement rate (IR) metric for comparing models. As a result, we compare the different forecasting models to the chosen benchmarking model to confirm the improvement trends for the model’s predictions.
This paper investigates the pricing of liquidity risk in the cross-section of cryptocurrencies from January 2017 to December 2020. The cryptocurrencies with high liquidity risk (beta) earned a risk-adjusted return of 4.4% higher weekly than those with low liquidity risk after controlling for the market, size, and reversal factors. Furthermore, the positive relation between expected cryptocurrency returns and liquidity risk is robust when I use cross-sectional regression tests for individual cryptocurrencies and alternative liquidity measures. The results suggest that liquidity risk is an important determinant of expected cryptocurrency returns.
Mnacho Echenim, Emmanuel Gobet, Anne-Claire Maurice
We design a novel calibration procedure that is designed to handle the specific characteristics of options on cryptocurrency markets, namely large bid-ask spreads and the possibility of missing or incoherent prices in the considered data sets. We show that this calibration procedure is significantly more robust and accurate than the standard one based on trade and mid-prices.
In recent years, machine learning and deep learning techniques have been frequently used in Algorithmic Trading. Algorithmic Trading means trading Forex, stock market, commodities, and many markets with the help of computers using systems created with various technical analysis indicators. The BTC/USD market is a market that allows buying and selling of products. People aim to profit by buying and selling in the Bitcoin market. Reinforcement Learning (RL) was also helpful in achieving those kinds of goals. Reinforcement learning is a sub-topic of machine learning. RL addresses the problem of a computational agent learning to make decisions by trial and error. For our application, it is aimed to make as much profit as possible. This study focuses on developing a novel tool to automate currency trading like a BTC/USD in a simulated market with maximum profit and minimum loss. RL technique with a modified version of the Collective Decision Optimization Algorithm is used to implement the proposed model. Feature engineering is also performed to create features that improve the result.
This study tests for the weak-form market efficiency of 15 cryptocurrency prices. The conventional unit root tests and stationary test results reveal that most cryptocurrency markets are efficient markets. However, the non-linear quantile unit root test proposed by Li and Park (2018) rejects the unit root null hypothesis over the whole quantile level. To derive more informative ideas, we split the whole quantile interval to several sub-intervals and find asymmetric behaviour of the market efficiency across the lower and upper sub-intervals in several cryptocurrency markets. Moreover, non-linear quantile unit root tests for Chainlink, Bitcoin Cash, Binance Coin, EOS, Tron, and Stellar indicate that markets for these cryptocurrencies are efficient at the upper sub-intervals.