A novel framework of credit risk feature selection for SMEs during industry 4.0.

With the development of industry 4.0, the credit data of SMEs are characterized by a large volume, high speed, diversity and low-value density. How to select the key features that affect the credit risk from the high-dimensional data has become the critical point to accurately measure the credit risk of SMEs and alleviate their financing constraints. In doing so, this paper proposes a credit risk feature selection approach that integrates the binary opposite whale optimization algorithm (BOWOA) and the Kolmogorov-Smirnov (KS) statistic. Furthermore, we use seven machine learning classifiers and three discriminant methods to verify the robustness of the proposed model by using three actual bank data from SMEs. The empirical results show that although no one artificial intelligence credit evaluation method is universal for different SMEs' credit data, the performance of the BOWOA-KS model proposed in this paper is better than other methods if the number of indicators in the optimal subset of indicators and the prediction performance of the classifier are considered simultaneously. By providing a high-dimensional data feature selection method and improving the predictive performance of credit risk, it could help SMEs focus on the factors that will allow them to improve their creditworthiness and more easily access loans from financial institutions. Moreover, it will also help government agencies and policymakers develop policies to help SMEs reduce their credit risks.

Work Resumption Rate and Migrant Workers' Income During the COVID-19 Pandemic.

The COVID-19 public health crisis has quickly led to an economic crisis, impacting many people and businesses in the world. This study examines how the pandemic affects workforces and workers' income. We quantify the impact of staggered resumption of work, after the coronavirus lockdowns, on the migrant workers' income. Using data on population movements of 366 Chinese cities at the daily level from the Baidu Maps-Migration Big Data Platform and historical data on the average monthly income of migrant workers, we find that the average work resumption rate (WRR) during the period of the Chinese Lantern Festival was 25.25%, which was only 30.67% of that in the same matched lunar calendar period in 2019. We then apply Gray Model First Order One Variable [GM (1, 1)] to predict the monthly income of migrant workers during the period of the COVID-19 pandemic. We show that, if without the influence of the COVID-19 pandemic, the average monthly income of migrant workers in 2020 will be expected to increase by 12% compared with 2019. We further conduct scenario analysis and show that the average monthly income of migrant workers in 2020 under the conservative scenario (COS), medium scenario (MES), and worse scenario (WOS) will be predicted to decrease by 2, 21, and 44%, respectively. Through testing, our prediction error is <5%. Our findings will help policymakers to decide when and how they implement a plan to ease the coronavirus lockdown and related financial support policies.

African swine fever outbreaks in China led to gross domestic product and economic losses.

African swine fever (ASF) is a fatal and highly infectious haemorrhagic disease that has spread to all provinces in China-the world's largest producer and consumer of pork. Here we use an input-output model, partial equilibrium theory and a substitution indicator approach for handling missing data to develop a systematic valuation framework for assessing economic losses caused by ASF outbreaks in China between August 2018 and July 2019. We show that the total economic loss accounts for 0.78% of China's gross domestic product in 2019, with impacts experienced in almost all economic sectors through links to the pork industry and a substantial decrease in consumer surplus. Scenario analyses demonstrate that the worst cases of pig production reduction and price increase would trigger 1.4% and 2.07% declines in gross domestic product, respectively. These findings demonstrate an urgent need for rapid ASF containment and prevention measures to avoid future outbreaks and economic declines.