Journal of Risk and Financial Management

Research

21 pages, 3991 KiB

Open AccessArticle

Picking Winners: Identifying Features of High-Performing Special Purpose Acquisition Companies (SPACs) with Machine Learning

by Caleb J. Williams

J. Risk Financial Manag. 2023, 16(4), 236; https://doi.org/10.3390/jrfm16040236 - 11 Apr 2023

Viewed by 1655

Abstract

Special Purpose Acquisition Companies (SPACs) are publicly listed “blank check” firms with a sole purpose: to merge with a private company and take it public. Selecting a target to take public via SPACs is a complex affair led by SPAC sponsors who seek [...] Read more.

Special Purpose Acquisition Companies (SPACs) are publicly listed “blank check” firms with a sole purpose: to merge with a private company and take it public. Selecting a target to take public via SPACs is a complex affair led by SPAC sponsors who seek to deliver investor value by effectively “picking winners” from the private sector. A key question for all sponsors is what they should be searching for. This paper aims to identify the characteristics of SPACs and their target companies that are relevant to market performance at sponsor lock-up windows. To achieve this goal, the study breaks market performance into a binary classification problem and uses a machine learning approach comprised of decision trees, logistic regression, and LASSO regression to identify features that exhibit a distinct relationship with market performance. The obtained results demonstrate that corporate or private equity backing in target firms greatly improves the odds of market outperformance one-year post-merger. This finding is novel in indicating that characteristics of target firms may also be deterministic of SPAC performance, in addition to SPACs, transaction, and the market features identified in the prior literature. It further suggests that a viable sponsor strategy could be constructed for generating outsized market returns at share lock-up windows by simply “following the money” and choosing target firms with prior involvement from corporate or private equity investors. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

9 pages, 715 KiB

Open AccessArticle

A Study of the Machine Learning Approach and the MGARCH-BEKK Model in Volatility Transmission

by Prashant Joshi, Jinghua Wang and Michael Busler

J. Risk Financial Manag. 2022, 15(3), 116; https://doi.org/10.3390/jrfm15030116 - 02 Mar 2022

Cited by 4 | Viewed by 2942

Abstract

This study analyzes the volatility spillover effects in the US stock market (S&P500) and cryptocurrency market (BGCI) using intraday data during the COVID-19 pandemic. As the potential drivers of portfolio diversification, we measure the asymmetric volatility transmission on both markets. We apply MGARCH-BEKK [...] Read more.

This study analyzes the volatility spillover effects in the US stock market (S&P500) and cryptocurrency market (BGCI) using intraday data during the COVID-19 pandemic. As the potential drivers of portfolio diversification, we measure the asymmetric volatility transmission on both markets. We apply MGARCH-BEKK and the algorithm-based

G A^{2} M

machine learning model. The negative shocks to returns impact the S&P500 and the cryptocurrency market more than the positive shocks on both markets. This study also indicates evidence of unidirectional cross-market asymmetric volatility transmission from the cryptocurrency market to the S&P500 during the COVID-19 pandemic. The research findings show the potential benefit of portfolio diversification between the S&P500 and BGCI. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

10 pages, 616 KiB

Open AccessArticle

Forecasting the Price of the Cryptocurrency Using Linear and Nonlinear Error Correction Model

by Jong-Min Kim, Chanho Cho and Chulhee Jun

J. Risk Financial Manag. 2022, 15(2), 74; https://doi.org/10.3390/jrfm15020074 - 10 Feb 2022

Cited by 8 | Viewed by 4489

Abstract

We employed linear and nonlinear error correction models (ECMs) to predict the log returns of Bitcoin (BTC). The linear ECM is the best model for predicting BTC compared to the neural network and autoregressive models in terms of RMSE, MAE, and MAPE. Using [...] Read more.

We employed linear and nonlinear error correction models (ECMs) to predict the log returns of Bitcoin (BTC). The linear ECM is the best model for predicting BTC compared to the neural network and autoregressive models in terms of RMSE, MAE, and MAPE. Using a linear ECM, we are able to understand how BTC is affected by other coins. In addition, we performed Granger-causality tests on fourteen cryptocurrencies. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

10 pages, 1509 KiB

Open AccessArticle

Univariate and Multivariate Machine Learning Forecasting Models on the Price Returns of Cryptocurrencies

by Dante Miller and Jong-Min Kim

J. Risk Financial Manag. 2021, 14(10), 486; https://doi.org/10.3390/jrfm14100486 - 14 Oct 2021

Cited by 9 | Viewed by 2550

Abstract

In this study, we predicted the log returns of the top 10 cryptocurrencies based on market cap, using univariate and multivariate machine learning methods such as recurrent neural networks, deep learning neural networks, Holt’s exponential smoothing, autoregressive integrated moving average, ForecastX, and long [...] Read more.

In this study, we predicted the log returns of the top 10 cryptocurrencies based on market cap, using univariate and multivariate machine learning methods such as recurrent neural networks, deep learning neural networks, Holt’s exponential smoothing, autoregressive integrated moving average, ForecastX, and long short-term memory networks. The multivariate long short-term memory networks performed better than the univariate machine learning methods in terms of the prediction error measures. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

24 pages, 1727 KiB

Open AccessArticle

A Novel Model Structured on Predictive Churn Methods in a Banking Organization

by Leonardo José Silveira, Plácido Rogério Pinheiro and Leopoldo Soares de Melo Junior

J. Risk Financial Manag. 2021, 14(10), 481; https://doi.org/10.3390/jrfm14100481 - 12 Oct 2021

Cited by 2 | Viewed by 2376

Abstract

A constant in the business world is the frequent movement of customers joining or abandoning companies’ services and products. The customer is one of the company’s most important assets. Reducing the customer abandonment rate has become a matter of survival and, at the [...] Read more.

A constant in the business world is the frequent movement of customers joining or abandoning companies’ services and products. The customer is one of the company’s most important assets. Reducing the customer abandonment rate has become a matter of survival and, at the same time, the most efficient way to maintain the customer base, since the replacement of dropouts by new customers costs, on average, 40% more. Aiming to mitigate the churn (customer evasion) phenomenon, this study compared predictive models to discover the most efficient method to identify customers who tend to drop out in the context of a banking organization. A literature review of related works on the subject found the neural network, decision tree, random forest and logistic regression models were the most cited, and thus the models were chosen for this work. Quantitative analyses were carried out on a sample of 200,000 credit operations, with 497 explanatory variables. The statistical treatment of the data and the developments of predictive models of churn were performed using the Orange data mining software. The most expressive results were achieved using the random forest model, with an accuracy of 82%. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

22 pages, 2531 KiB

Open AccessArticle

Anchoring and Asymmetric Information in the Real Estate Market: A Machine Learning Approach

by Ka Shing Cheung, Julian TszKin Chan, Sijie Li and Chung Yim Yiu

J. Risk Financial Manag. 2021, 14(9), 423; https://doi.org/10.3390/jrfm14090423 - 04 Sep 2021

Cited by 10 | Viewed by 4035

Abstract

Conventional wisdom suggests that non-local buyers usually pay a premium for home purchases. While the standard contract theory predicts that non-local buyers may pay such a price premium because of the higher cost of gathering information, behavioral economists argue that the premium is [...] Read more.

Conventional wisdom suggests that non-local buyers usually pay a premium for home purchases. While the standard contract theory predicts that non-local buyers may pay such a price premium because of the higher cost of gathering information, behavioral economists argue that the premium is due to buyer anchoring biases in relation to the information. Both theories support such a price premium proposition, but the empirical evidence is mixed. In this study, we revisit this conundrum and put forward a critical test of these two alternative hypotheses using a large-scale housing transaction dataset from Hong Kong. A novel machine-learning algorithm with the latest technique in natural language processing where applicable to multi-languages is developed for identifying non-local Mainland Chinese buyers and sellers. Using the repeat-sales method that avoids omitted variable biases, non-local buyers (sellers) are found to buy (sell) at a higher (lower) price than their local counterparts. Taking advantage of a policy change in transaction tax specific to non-local buyers as a quasi-experiment and utilizing the local buyers as counterfactuals, we found that the non-local price premium switches to a discount after the policy intervention. The result implies that the hypothesis of anchoring biases is dominant. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

22 pages, 3155 KiB

Open AccessArticle

GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies

by Fahad Mostafa, Pritam Saha, Mohammad Rafiqul Islam and Nguyet Nguyen

J. Risk Financial Manag. 2021, 14(9), 421; https://doi.org/10.3390/jrfm14090421 - 03 Sep 2021

Cited by 18 | Viewed by 4648

Abstract

Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement GJR-GARCH over the GARCH model to estimate the volatility of [...] Read more.

Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement GJR-GARCH over the GARCH model to estimate the volatility of ten popular cryptocurrencies based on market capitalization: Bitcoin, Bitcoin Cash, Bitcoin SV, Chainlink, EOS, Ethereum, Litecoin, TETHER, Tezos, and XRP. Then, we use Monte Carlo simulations to generate the conditional variance of the cryptocurrencies using the GJR-GARCH model, and calculate the value at risk (VaR) of the simulations. We also estimate the tail-risk using VaR backtesting. Finally, we use an artificial neural network (ANN) for predicting the prices of the ten cryptocurrencies. The graphical analysis and mean square errors (MSEs) from the ANN models confirmed that the predicted prices are close to the market prices. For some cryptocurrencies, the ANN models perform better than traditional ARIMA models. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

21 pages, 2571 KiB

Open AccessArticle

Predicting Gold and Silver Price Direction Using Tree-Based Classifiers

by Perry Sadorsky

J. Risk Financial Manag. 2021, 14(5), 198; https://doi.org/10.3390/jrfm14050198 - 29 Apr 2021

Cited by 18 | Viewed by 5193

Abstract

Gold is often used by investors as a hedge against inflation or adverse economic times. Consequently, it is important for investors to have accurate forecasts of gold prices. This paper uses several machine learning tree-based classifiers (bagging, stochastic gradient boosting, random forests) to [...] Read more.

Gold is often used by investors as a hedge against inflation or adverse economic times. Consequently, it is important for investors to have accurate forecasts of gold prices. This paper uses several machine learning tree-based classifiers (bagging, stochastic gradient boosting, random forests) to predict the price direction of gold and silver exchange traded funds. Decision tree bagging, stochastic gradient boosting, and random forests predictions of gold and silver price direction are much more accurate than those obtained from logit models. For a 20-day forecast horizon, tree bagging, stochastic gradient boosting, and random forests produce accuracy rates of between 85% and 90% while logit models produce accuracy rates of between 55% and 60%. Stochastic gradient boosting accuracy is a few percentage points less than that of random forests for forecast horizons over 10 days. For those looking to forecast the direction of gold and silver prices, tree bagging and random forests offer an attractive combination of accuracy and ease of estimation. For each of gold and silver, a portfolio based on the random forests price direction forecasts outperformed a buy and hold portfolio. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

19 pages, 3378 KiB

Open AccessArticle

Movie Title Keywords: A Text Mining and Exploratory Factor Analysis of Popular Movies in the United States and China

by Xingyao Xiao, Yihong Cheng and Jong-Min Kim

J. Risk Financial Manag. 2021, 14(2), 68; https://doi.org/10.3390/jrfm14020068 - 06 Feb 2021

Cited by 4 | Viewed by 4069

Abstract

Unprecedented opportunities have been brought by advancements in machine learning in the prediction of the economic success of movies. The analysis of movie title keywords is one promising but rarely investigated direction of study. To address this gap, we performed a text mining [...] Read more.

Unprecedented opportunities have been brought by advancements in machine learning in the prediction of the economic success of movies. The analysis of movie title keywords is one promising but rarely investigated direction of study. To address this gap, we performed a text mining and exploratory factor analysis (EFA) of the relationships between movie titles and their corresponding movies’ levels of success. Specifically, intragroup and intergroup analyses of 217 top hit movies in the United States and 245 top hit movies in China showed that successful movies in these two major movie markets with outstanding total lifetime grosses featured titles with similar and different patterns of most frequently used words, revealing useful information about viewers’ preferences in these countries. The findings of this study will serve to better inform the movie industry in giving more economically promising names to their products from a machine-learning perspective and inspire further studies. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

15 pages, 529 KiB

Open AccessArticle

Observation Time Effects in Reinforcement Learning on Contracts for Difference

by Maximilian Wehrmann, Nico Zengeler and Uwe Handmann

J. Risk Financial Manag. 2021, 14(2), 54; https://doi.org/10.3390/jrfm14020054 - 27 Jan 2021

Viewed by 2267

Abstract

In this paper, we present a study on Reinforcement Learning optimization models for automatic trading, in which we focus on the effects of varying the observation time. Our Reinforcement Learning agents feature a Convolutional Neural Network (CNN) together with Long Short-Term Memory (LSTM) [...] Read more.

In this paper, we present a study on Reinforcement Learning optimization models for automatic trading, in which we focus on the effects of varying the observation time. Our Reinforcement Learning agents feature a Convolutional Neural Network (CNN) together with Long Short-Term Memory (LSTM) and act on the basis of different observation time spans. Each agent tries to maximize trading profit by buying or selling one of a number of contracts in a simulated market environment for Contracts for Difference (CfD), considering correlations between individual assets by architecture. To decide which action to take on a specific contract, an agent develops a policy which relies on an observation of the whole market for a certain period of time. We investigate whether or not there exists an optimal observation sequence length, and conclude that such a value depends on market dynamics. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

29 pages, 2783 KiB

Open AccessArticle

Know Your Clients’ Behaviours: A Cluster Analysis of Financial Transactions

by John R. J. Thompson, Longlong Feng, R. Mark Reesor and Chuck Grace

J. Risk Financial Manag. 2021, 14(2), 50; https://doi.org/10.3390/jrfm14020050 - 25 Jan 2021

Cited by 8 | Viewed by 7520

Abstract

In Canada, financial advisors and dealers are required by provincial securities commissions and self-regulatory organizations—charged with direct regulation over investment dealers and mutual fund dealers—to respectively collect and maintain know your client (KYC) information, such as their age or risk tolerance, for investor [...] Read more.

In Canada, financial advisors and dealers are required by provincial securities commissions and self-regulatory organizations—charged with direct regulation over investment dealers and mutual fund dealers—to respectively collect and maintain know your client (KYC) information, such as their age or risk tolerance, for investor accounts. With this information, investors, under their advisor’s guidance, make decisions on their investments that are presumed to be beneficial to their investment goals. Our unique dataset is provided by a financial investment dealer with over 50,000 accounts for over 23,000 clients covering the period from January 1st to August 12th 2019. We use a modified behavioral finance recency, frequency, monetary model for engineering features that quantify investor behaviours, and unsupervised machine learning clustering algorithms to find groups of investors that behave similarly. We show that the KYC information—such as gender, residence region, and marital status—does not explain client behaviours, whereas eight variables for trade and transaction frequency and volume are most informative. Hence, our results should encourage financial regulators and advisors to use more advanced metrics to better understand and predict investor behaviours. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Graphical abstract

21 pages, 1537 KiB

Open AccessArticle

The Changing Dynamics of Board Independence: A Copula Based Quantile Regression Approach

by Jong-Min Kim, Chanho Cho, Chulhee Jun and Won Yong Kim

J. Risk Financial Manag. 2020, 13(11), 254; https://doi.org/10.3390/jrfm13110254 - 28 Oct 2020

Viewed by 1855

Abstract

This paper examines the effect of board characteristics, especially board independence, on firm performance from a dynamic perspective through copula-based quantile regression approaches, which allow us to focus on changes at different points in the distribution of board characteristics. We find that the [...] Read more.

This paper examines the effect of board characteristics, especially board independence, on firm performance from a dynamic perspective through copula-based quantile regression approaches, which allow us to focus on changes at different points in the distribution of board characteristics. We find that the effect of board independence on Tobin’s Q, a proxy of firm value, is negatively associated with firm value, using ordinary least squares (OLS) regression. This negative effect using the conditional mean of the firm value does not hold across the conditional quantiles of the distribution of Tobin’s Q, and this finding is still held under both the linear and the nonlinear quantile regressions. We even lessen the assumption of distributions of multivariate board variables by employing parametric copula-based quantile regressions as well as nonparametric ones. The results support our findings. Our results suggest that estimating the quantile effect of board variables on firm value can provide more meaningful insight than just examining the conditional mean effect. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

11 pages, 241 KiB

Open AccessArticle

Use of Machine Learning Techniques to Create a Credit Score Model for Airtime Loans

by Bernard Dushimimana, Yvonne Wambui, Timothy Lubega and Patrick E. McSharry

J. Risk Financial Manag. 2020, 13(8), 180; https://doi.org/10.3390/jrfm13080180 - 13 Aug 2020

Cited by 11 | Viewed by 6717

Abstract

Airtime lending default rates are typically lower than those experienced by banks and microfinance institutions (MFIs) but are likely to grow as the service is offered more widely. In this paper, credit scoring techniques are reviewed, and that knowledge is built upon to [...] Read more.

Airtime lending default rates are typically lower than those experienced by banks and microfinance institutions (MFIs) but are likely to grow as the service is offered more widely. In this paper, credit scoring techniques are reviewed, and that knowledge is built upon to create an appropriate machine learning model for airtime lending. Over three million loans belonging to more than 41 thousand customers with a repayment period of three months are analysed. Logistic Regression, Decision Trees and Random Forest are evaluated for their ability to classify defaulters using several cross-validation approaches and the latter model performed best. When the default rate is below 2%, it is better to offer everyone a loan. For higher default rates, the model substantially enhances profitability. The model quadruples the tolerable level of default rate for breaking even from 8% to 32%. Nonlinear classification models offer considerable potential for credit scoring, coping with higher levels of default and therefore allowing for larger volumes of customers. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

7 pages, 348 KiB

Open AccessCommunication

Cryptocurrency Trading Using Machine Learning

by Thomas E. Koker and Dimitrios Koutmos

J. Risk Financial Manag. 2020, 13(8), 178; https://doi.org/10.3390/jrfm13080178 - 10 Aug 2020

Cited by 26 | Viewed by 13773

Abstract

We present a model for active trading based on reinforcement machine learning and apply this to five major cryptocurrencies in circulation. In relation to a buy-and-hold approach, we demonstrate how this model yields enhanced risk-adjusted returns and serves to reduce downside risk. These [...] Read more.

We present a model for active trading based on reinforcement machine learning and apply this to five major cryptocurrencies in circulation. In relation to a buy-and-hold approach, we demonstrate how this model yields enhanced risk-adjusted returns and serves to reduce downside risk. These findings hold when accounting for actual transaction costs. We conclude that real-world portfolio management application of the model is viable, yet, performance can vary based on how it is calibrated in test samples. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Graphical abstract

20 pages, 777 KiB

Open AccessArticle

A Machine Learning Integrated Portfolio Rebalance Framework with Risk-Aversion Adjustment

by Zhenlong Jiang, Ran Ji and Kuo-Chu Chang

J. Risk Financial Manag. 2020, 13(7), 155; https://doi.org/10.3390/jrfm13070155 - 16 Jul 2020

Cited by 12 | Viewed by 5776

Abstract

We propose a portfolio rebalance framework that integrates machine learning models into the mean-risk portfolios in multi-period settings with risk-aversion adjustment. In each period, the risk-aversion coefficient is adjusted automatically according to market trend movements predicted by machine learning models. We employ Gini’s [...] Read more.

We propose a portfolio rebalance framework that integrates machine learning models into the mean-risk portfolios in multi-period settings with risk-aversion adjustment. In each period, the risk-aversion coefficient is adjusted automatically according to market trend movements predicted by machine learning models. We employ Gini’s Mean Difference (GMD) to specify the risk of a portfolio and use a set of technical indicators generated from a market index (e.g., S&P 500 index) to feed the machine learning models to predict market movements. Using a rolling-horizon approach, we conduct a series of computational tests with real financial data to evaluate the performance of the machine learning integrated portfolio rebalance framework. The empirical results show that the XGBoost model provides the best prediction of market movement, while the proposed portfolio rebalance strategy generates portfolios with superior out-of-sample performances in terms of average returns, time-series cumulative returns, and annualized returns compared to the benchmarks. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

12 pages, 1252 KiB

Open AccessArticle

Finding Nemo: Predicting Movie Performances by Machine Learning Methods

by Jong-Min Kim, Leixin Xia, Iksuk Kim, Seungjoo Lee and Keon-Hyung Lee

J. Risk Financial Manag. 2020, 13(5), 93; https://doi.org/10.3390/jrfm13050093 - 09 May 2020

Cited by 3 | Viewed by 4894

Abstract

Analyzing the success of movies has always been a popular research topic in the film industry. Artificial intelligence and machine learning methods in the movie industry have been applied to modeling the financial success of the movie industry. The new contribution of this [...] Read more.

Analyzing the success of movies has always been a popular research topic in the film industry. Artificial intelligence and machine learning methods in the movie industry have been applied to modeling the financial success of the movie industry. The new contribution of this research combined Bayesian variable selection and machine learning methods for forecasting the return on investment (ROI). We also attempt to compare machine learning methods including the quantile regression model with movie performance data in terms of in-sample and out of sample forecasting. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

16 pages, 3130 KiB

Open AccessArticle

A Gated Recurrent Unit Approach to Bitcoin Price Prediction

by Aniruddha Dutta, Saket Kumar and Meheli Basu

J. Risk Financial Manag. 2020, 13(2), 23; https://doi.org/10.3390/jrfm13020023 - 03 Feb 2020

Cited by 101 | Viewed by 13306

Abstract

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 [...] Read more.

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. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

14 pages, 497 KiB

Open AccessArticle

What Coins Lead in the Cryptocurrency Market: Using Copula and Neural Networks Models

by Steve Hyun, Jimin Lee, Jong-Min Kim and Chulhee Jun

J. Risk Financial Manag. 2019, 12(3), 132; https://doi.org/10.3390/jrfm12030132 - 08 Aug 2019

Cited by 16 | Viewed by 5118

Abstract

Exploring dependence structures between financial time series has been important within a wide range of applications. The main aim of this paper is to examine dependence relationships among five well-known cryptocurrencies—Bitcoin, Ethereum, Litecoin, Ripple, and Stella—by a copula directional dependence (CDD). By employing [...] Read more.

Exploring dependence structures between financial time series has been important within a wide range of applications. The main aim of this paper is to examine dependence relationships among five well-known cryptocurrencies—Bitcoin, Ethereum, Litecoin, Ripple, and Stella—by a copula directional dependence (CDD). By employing a neural network autoregression model to avoid the serial dependence in each individual cryptocurrency, we generate residuals of the fitted models with time series of daily log-returns in percentage of the five cryptocurrencies and then we apply a Gaussian copula marginal beta regression model to the residuals to explore the CDD. The results show that the CDD from Bitcoin to Litecoin is highest among all ordered directional dependencies and the CDDs from Ethereum to the other four cryptocurrencies are relatively higher than the CDDs to Ethereum from those cryptocurrencies. This finding implies that the return shocks of Bitcoin have the most effect on Litecoin and the return shocks of Ethereum relatively influence the shocks on the other four cryptocurrencies instead of being affected by them. This allows investors to build the market-timing strategies by observing the directional flow of return shocks among cryptocurrencies. Full article

(This article belongs to the Special Issue Machine Learning Applications in Finance)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Machine Learning Applications in Finance

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Related Special Issue

Published Papers (18 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI