The risk interdependence of cryptocurrencies: Before and during the COVID-19 pandemic

In this paper, we measure the risk interdependence of 12 major cryptocurrencies before and during the COVID-19 pandemic, based on a GARCH-Copula-VaR approach and a dynamic network analysis. We find that cryptocurrencies generally show high levels of volatility, speculation, homogeneity and tail risk contagion. Furthermore, the COVID-19 pandemic has a continuous impact on the cryptocurrency market. When financial institutions are increasingly investing in crypto assets, the hidden risks in the cryptocurrency market remain high. Therefore, this paper calls for attention on the cryptocurrency market from both investors and regulators.

Optimistic and pessimistic economic sentiments and US Dollar exchange rate

This study investigates the affiliation of various proxies of economic sentiments and the US Dollar exchange rate, mainly focusing on the real effective exchange rate of USD pairing with three other major currencies (USDEUR, USDGBP, and USDCAD). The study has employed Google Trends data of economy optimistic and pessimistic sentiments index and survey-based economy sentiments data on monthly basis from January 2004 to December 2018. The study engaged Ordinary Least Squares (OLS) and Auto-Regressive Distributed Lag (ARDL) estimation techniques to evaluate the short-run and long-run effects of economy-related sentiments and macroeconomic variables on the exchange rate. The results from the study found that Economy Optimistic Sentiments Index (EOSI) and Economy Pessimistic Sentiments Index (EPSI) appreciate and depreciate the US Dollar exchange rate in the short-run, respectively. Our sentiment measures are robust to survey-based Michigan Consumer Sentiment Index (MSCI), Consumer Confidence Index (CCI), and various macroeconomic factors. The MSCI and CCI sentiments show a long-term impact on the foreign exchange market. This study implies that economic sentiments play a vital role in the foreign exchange market and it is essential to consider behavioral aspects when modeling the exchange rate movements.

Identification of best discrimination surface by mixed-integer semi-definite programming for support vector machine

This paper proposes two improvements to the support vector machine (SVM): (i) extension to a semi-positive definite quadratic surface, which improves the discrimination accuracy; (ii) addition of a variable selection constraint. However, this model is formulated as a mixed-integer semi-definite programming (MISDP) problem, and it cannot be solved easily. Therefore, we propose a heuristic algorithm for solving the MISDP problem efficiently and show its effectiveness by using corporate credit rating data.

Liquidity-free implied volatilities: An approach using conic finance

In this paper, we consider the problem of calculating risk-neutral implied volatilities of European options without relying on option mid prices but solely on bid and ask prices. We provide an approach, based on the conic finance paradigm, that allows to uniquely strip risk-neutral implied volatilities from bid and ask quotes, and that does not require restrictive assumptions. Our methodology also allows to jointly calculate the implied liquidity of the market. The idea outlined in this paper can be applied to calculate other implied parameters from bid and ask security prices as soon as their theoretical risk-neutral counterparts are strictly increasing with respect to the former.

Deep learning neural network for the prediction of asian tiger stock markets

Motivated by the recent interest of stock traders and investors towards the deep learning neural network, this study employs the deep learning neural networks, namely, multilayer perceptron, long short-term memory, and convolutional neural network, to forecast the Asian Tiger stock markets. One of the challenges to using deep learning neural networks is to select the input variable. We propose to use multiple linear regression to select the input variable that is significant to the output. Besides, we construct a regional stock market index as a significant input to forecast the Asian Tiger stock markets. A comparison study on the forecasting model shows that the deep learning model can be used as a decision-making system that assists investors to predict short-term movement and trends of stock prices.

Optimal trading: The importance of being adaptive

We compare optimal static and dynamic solutions in trade execution. An optimal trade execution problem is considered where a trader is looking at a short-term price predictive signal while trading. When the trader creates an instantaneous market impact, it is shown that transaction costs of optimal adaptive strategies are substantially lower than the corresponding costs of the optimal static strategy. In the same spirit, in the case of transient impact, it is shown that strategies that observe the signal a finite number of times can dramatically reduce the transaction costs and improve the performance of the optimal static strategy.

A federated interpretable scorecard and its application in credit scoring

In this paper, we propose a vertical federated learning (VFL) structure for logistic regression with bounded constraint for the traditional scorecard, namely FL-LRBC. Under the premise of data privacy protection, FL-LRBC enables multiple agencies to jointly obtain an optimized scorecard model in a single training session. It leads to the formation of scorecard model with positive coefficients to guarantee its desirable characteristics (e.g., interpretability and robustness), while the time-consuming parameter-tuning process can be avoided. Moreover, model performance in terms of both AUC and the Kolmogorov–Smirnov (KS) statistics is significantly improved by FL-LRBC, due to the feature enrichment in our algorithm architecture. Currently, FL-LRBC has already been applied to credit business in a China nation-wide financial holdings group.

Does Local Legal Environment Matter in the Online Credit Market?

The physical distance and fragile relationship between online debtors and online creditors make legal enforcement less intimidating; therefore, the role of the legal environment in the online credit market is a topic worth investigating. This paper employs an online lending platform and uses loan-level data to investigate the local legal environment’s effect in the online credit market. We find that a favorable legal environment can motivate online debtors’ integrity, improve online debtors’ credit availability and reduce online debtors’ loan costs, implying the positive externalities of the legal environment’s progress. Finally, we confirm that online debtors with lower income and large loan amounts benefit more from the legal environment’s progress. Our finding indicates that even though fintech has profoundly changed the organizational form and transaction mode of financial institutions, the legal environment still plays an essential role in promoting inclusive finance.

Dynamic efficiency of China’s commodity futures market through the lens of high frequency data

In this paper, we use the permutation entropy algorithm to derive the static and dynamic permutation entropy of commodity futures, and to evaluate the effectiveness of main products in China’s commodity futures market. The intraday data of six varieties belonging to six categories in China’s commodity futures market are taken as samples. We find the following: (1) The return distribution of the main varieties shows high peaks, fat tails and asymmetry, and follows the biased random walk distribution characteristics; (2) The permutation entropy of all varieties decreases significantly in the same time window, during which the price volatility of major commodity markets rises. And the time window coincides with the impact time of COVID-19 epidemic; (3) By comparing the distribution of permutation entropy of main varieties in different stages of event shock, we found that the mean value of permutation entropy decreases significantly during the process of event shock, and the price fluctuates greatly. Therefore, the significant decrease of permutation entropy is a valuable warning signal for regulators and investors.