Over the past two years, COVID-19 pandemic has swept across the world, causing varying degrees of shocks and impacts on the whole society and various sectors of the world. In the process of the epidemic evolving and human fighting against the virus, new problems and challenges are constantly emerging. Scholars, universities and research institutions around the world are committed to discovering, analyzing and solving problems in various fields brought about by the epidemic, and keep to move forward.

In many studies for problems related to COVID-19, the support of data science is important. The scientific principles, important methods and cutting-edge technologies such as quantitative models, statistical analysis, and data mining provide the basis for analyzing and solving problems. With the theme of “COVID-19 and its impacts”, this special issue presents some contributed researches which use statistical models, machine learning and other data science knowledge to analyze problems related to COVID-19. The issue consists of 11 papers, covering researches on epidemic evolution and prediction models (papers 2, 3, 4, 7, and 11), the impacts of COVID-19 on the economy and financial markets (papers 1, 5, 6, and 9), and epidemic prevention and control (papers 8, and 10). Some of them provide new statistical methods, while some analyze and solve practical problems during the pandemic. The studies all provide certain theoretical and practical significance.

The first paper, “Global Economic Impact in Stock and Commodity Markets during Covid-19 pandemic” by Arhan Sheth, Tulasi Sushra, Ameya Kshirsagar and Manan Shah, analyses and summarizes the impacts of COVID-19 on the stock and commodity markets around the globe based on existing researches. According to examples and studies from different countries, the authors discuss different reactions and policies of various regions under the shock of the epidemic. The COVID-19 pandemic has caused an adverse shock and low investments on the stock market, and the prices of most commodities have shown upward trends. Moreover, the paper analyses the future changes and the challenges that might be faced by the markets due to the evolution of the epidemic. The second paper, “The Exponentiated Gumbel–Weibull {Logistic} Distribution with Application to Nigeria’s COVID-19 Infections Data” by Patrick Osatohanmwen, Eferhonore Efe-Eyefia, Francis O. Oyegue, Joseph E. Osemwenkhae, Sunday M. Ogbonmwan and Benson A. Afere, proposes a new flexible univariate probability distribution, called the ‘exponentiated Gumbel–Weibull {logistic} distribution’, and applies it to study the daily number of COVID-19 infections in Nigeria. The distribution is modeled by using the exponentiated Gumbel distribution to generate a generalized Weibull distribution with the logit function or the quantile function of the logistic distribution as a link, which shows both unimodal and bimodal as well as various shape and tail properties. The experiments on five other datasets demonstrate flexibility of the distribution and good fitting results of real-life data. The third paper, “Data Analysis of COVID-19 Hospital Records Using Contextual Patient Classification System” by Vrushabh Gada, Madhura Shegaonkar, and Madhura Inamdar et al., proposes a contextual patient classification system for better analyzing the data of COVID-19 and non-COVID-19 patients from the hospital. The system helps to filter and rearrange the raw data, classify COVID-19 and non-COVID-19 patients by KMP algorithm, and analyze and visualize the differences in various aspects between COVID-19 and non-COVID-19 patients. The classification accuracy of the contextual patient classification system achieves 97.4%, which helps doctors in faster diagnosis and predicts the future waves of the COVID-19 pandemic.

The fourth paper, “Effective Learning During COVID-19: Multilevel Covariates Matching and Propensity Score Matching” by Siying Guo, Jianxuan Liu, and Qiu Wang, studies a covariates matching method and develops a generalized propensity score matching method to reduce the bias of estimation in the intervention effect. The simple algorithms are proposed to assess the covariates balance for each approach, and the finite sample performance of the methods are analyzed by simulation studies. The proposed method is applied to analyze the hybrid learning data during the COVID-19 pandemic and shows obvious effectiveness. The fifth paper, “The Impact of COVID-19 on China’s Capital Market and Major Industry Sectors” by Weijia Xu, Aihua Li, and Lu Wei, investigates the impact of COVID-19 on China’s capital markets and major industry sectors by the improved ICSS algorithm, the time series model and nonparametric conditional probability estimation. The results of empirical studies show that the pandemic has had less influence on returns of the stock and bond markets but large shocks on the market volatilities. For different industry sectors, the impacts of COVID-19 show obvious differences in the significance, direction and duration. The sixth paper, “Dynamic Interaction of COVID-19 Incidence and Stock Market Performance: Evidence from Nigeria” by Lukman O. Oyelami, Matthew I. Ogbuagu, and Olufemi M. Saibu, studies the dynamic interaction of COVID-19 incidence and stock market performance in Nigeria using vector autoregressive model based on the daily time series data of All Share Index (ASI), COVID-19 pandemic confirmed cases, Nigerian borrowing rate and exchange rate. The empirical results show that the lagged value of COVID-19 infections has significant negative influence on ASI; apart from some small and medium enterprises, the stock market in Nigerian has been generally shocked by the epidemic.

The seventh paper, “Forecasting the Trends of Covid-19 and Causal Impact of Vaccines Using Bayesian Structural Time Series and ARIMA” by Muhammed Navas Thorakkattle, Shazia Farhin, and Athar Ali khan, uses the Bayesian structural time series model to forecast the COVID-19 trends of five different countries, and analyzes the casual effect of vaccines. The authors predict the number of confirmed cases and the death rates of five countries and show the decrease of the death rate with effective and quick vaccination in some countries. The eighth paper, “What country, university, or research institute, performed the best on COVID-19 during the first wave of the pandemic?” by Petar Radanliev, David De Roure, and Rob Walton et al., conducts data mining and statistical analysis on the most effective countries, universities, and companies, based on their output on COVID-19 during the first wave of the pandemic. Through the results from bibliometric science mapping based on three different data mining methods, the authors present visualizations of the research connections between areas and countries, and analyze the emerging patterns and the speeds of national responses. The ninth paper, “Content Analysis of the Economic Problems of Covid-19 Disease on Businesses: A Case Study of Tehran Province, Iran” by Vali Borimnejad and Sahar Dehyouri, investigates the impacts of COVID-19 on the domestic economy in Iran from the service, industry and agriculture sectors. The authors conduct surveys to collect data from 7387 businesses, and the questionnaire problems are related to loans, liquidity, facilities, taxes, aid and grants, government support and assistance, and so on. Some practical suggestions are obtained in the end of the paper based on the result analysis.

The tenth paper, “Self-care, Household Cleaning and Disinfection During COVID-19 Pandemic: A Study from Metropolitan Cities of India” by Vaishali Chaurasia, Ajay Gupta, Ratna Patel, Shekhar Chauhan, Nitesh Kumar Adichwal, and Sachin Kamble, conducts the self-administered questionnaire survey to analyze people’s hygienic practices such as self-care, household cleaning and disinfection by the quota sampling technique and bivariate analysis. Based on the findings, disseminating the information on the use of unhealthy disinfectants, and promoting further knowledge on risk factors of COVID-19 and healthy hand hygiene among people are necessary and urgent. The eleventh paper, “Three-Inflated Poisson Distribution and its Application in Suicide Cases of India During Covid-19 Pandemic” by Tousifur Rahman, Partha Jyoti Hazarika, M. Masoom Ali and Manash Pratim Barman, proposes a three-inflated Poisson distribution, which mixes the Poisson distribution and a distribution to a point mass at three, and demonstrates distribution properties and reliability characteristics of the model. The authors use COVID-19 related suicide data of India from lockdown to unlocking 1.0 to fit the proposed distribution and verify the usefulness of it.

At present, remarkable achievements have been made in the fight against COVID-19 by human beings, and scientific researches in all kinds of fields are no exception, which have helped solve many difficult problems and provided strong support for practice. It is of great significance for providing useful information regarding the pandemic and predicting the future evolution, combatting and controlling the epidemic, supporting the policy making. AODS encourages more contributors around the world to address different challenging problems of COVID-19 in various aspects using advanced data science and technologies.