Search

The credit risk of small and medium‐sized enterprises (SMEs) in supply chain finance (SCF) hinders the sustainability of the supply chain and threatens the monetary loss of SCF partners, that is, focal enterprises (FEs) and financial institutions (FIs). Thus, it is crucial to predict SMEs' credit risk accurately. However, redundant features and imbalanced sample data may decrease the accuracy of the prediction model. Therefore, a novel credit risk prediction framework is proposed called FS‐RS‐ML, which is short for Feature Selection–Resample Strategy–Machine Learning. In this approach, Recursive Feature Elimination with Cross‐Validation (RFECV) is applied to select key features influencing SMEs' credit risk prediction, and three resampling techniques are used to balance the sample data. Finally, five machine learning algorithms are adopted to classify high‐risk and low‐risk SMEs. The experiments based on Chinese SCF data demonstrate that the FS‐RS‐ML framework outperforms any single algorithm. Moreover, according to the analysis of empirical results, features derived from SMEs have the most important impact on credit risk prediction. And the effect of key features on predicting SMEs' credit risk is revealed. [ABSTRACT FROM AUTHOR]

This article aims to reveal the subsistence economy of the Qin and Han empires and why they continued to advance northward to defeat the Huns (Xiongnu 匈奴) and other grassland peoples in the Ordos Plateau. We present the δ13C and δ15N results for the dietary reconstruction of animals and humans from the Fuluta cemetery in the Ordos Plateau, a nomadic farming junction area, from the late Qin dynasty (221–207 BCE) to the Western Han dynasty (202 BCE to 8 AD). Results show that the δ13C and δ15N values for humans (−8.5 ± 0.4‰, 9.2 ± 0.5‰, n = 29), pigs (−8.6 ± 1.4‰, 7.7 ± 1.1‰, n = 3) and dogs (−9.1 ± 0.3‰, 7.7 ± 0.4‰, n = 3) were generally higher than those for cattle (−15.7 ± 1.4‰, 6.5 ± 1.0‰, n = 8) and sheep (−17.8 ± 0.9‰, 6.2 ± 1.6‰, n = 11), indicating humans, pigs and dogs may have relied primarily on C4‐based food (millet), whereas cattle and sheep mainly relied on C3‐based food (wild plants). Related research shows that the diet of the population of the Fuluta cemetery was relatively homogenous and mainly based on millet agriculture and domestic animals, such as pigs, indicating that millet‐based agriculture was narrowly focused on for subsistence in the frontier region of northern China. The results of stable isotope work of the past populations in the surrounding areas of the Ordos Plateau from the period of the late Western Zhou dynasty (1046–771 BCE) to the Han dynasties (202 BCE to 220 AD) show trends of northward advancement and stability of the agricultural economy were constantly strengthening. Therefore, agriculturalization in the Ordos Plateau may have been the motivating force for Qin and Han imperial expansion into the frontier region. [ABSTRACT FROM AUTHOR]

Yangshao culture, as the most important Neolithic culture in China, is famous for its finely decorated pottery. In this work, Yangshao potteries excavated in Shanxi province, one of the core distribution areas, were studied by micro‐Raman spectroscopy combined with optical microscopy, X‐ray fluorescence, and scanning electron microscopy equipped with energy‐dispersive X‐ray spectroscopy. The color of the red decor is derived from hematite and maghemite. The black decorations on the surface are more complex, which could be divided into two types according to the Mn/Fe ratios and crystalline types: (1) low MnO2/Fe2O3 ratio and jacobsite and magnetite and (2) high MnO2/Fe2O3 ratio and hausmannite. The former color is obviously brighter than the latter. This study also demonstrates the potential of micro‐Raman microscopy in analyzing the nature of colorant crystals in Yangshao painted potteries and, therefore, better deciphering the technical details involved in the potteries of Yangshao culture. [ABSTRACT FROM AUTHOR]