Application of Two-stage Classification Method Based on K-means Function Clustering
            Algorithm in Financial Management

Ouyang, Tianhao; Lu, Xin

doi:10.46719/dsa202029348

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secondly, when the clusters are highly dense with nonsignificant differences, K-means can produce well clustering results. Below are how clusters are determined by K-means method [16].…”

Section: K-means Clustering Methodmentioning

confidence: 99%

Clustering Analysis of Risk Divergence of China Government’s Debts

Ouyang

2021

Scientific Programming

Self Cite

View full text Add to dashboard Cite

It is a difficult time for the world’s economics while the impact of COVID-19 is undergoing. A possible worldwide sovereign debt crisis could emerge, in short term, for supply chains blockage due to its slowing-down in many countries. China, having the second largest economy in the world, is crucial for the stability and sustainability of the economic recovery. China endures a long-term growth since 2000; nevertheless, a large amount of that growth is contributed by the government debt, which was spent on infrastructures. The accumulation of debts is a potential risk to the future growth of China. This research evaluates the central government and local government debts with a series of indicators. The weights of indicators are determined by objective methods of the CRITIC approach. Results confirm that the central government debt of China is on the edge of risk, while the risk of local governments debt is already in a concerning danger. The local government risk is 50% higher than the central government’s risk. Moreover, the K-means clustering algorithm performed on data, collected from various provinces, suggests that the local government debts of China follow a pattern of geographical distribution; that is, the closer to the coast, the lesser the risk, which is in accordance with the pattern of labor flowing. Labors are attracted by job opportunities which lie in the well-developed regions of China. This is confirmed by the crosscheck with the wage growth data. This indicates that the less developed areas of China rely more heavily on debt-investment stimulation that could be of a potential stagnation because the yield of investment follows diminishing marginal returns and the relative lacking labor weakens the potential economic growth.

show abstract

“…Secondly, when the clusters are highly dense with nonsignificant differences, K-means can produce well clustering results. Below are how clusters are determined by K-means method [16].…”

Section: K-means Clustering Methodmentioning

confidence: 99%