In this paper, cluster analysis was conducted for borrowers, based on information from the Korean Consumer Credit Panel (KCCP) for the period 2010–2016, using a self-organizing map (SOM) that visualizes individuals’ characteristics along two dimensions. The cluster analysis showed that most borrowers belonged to one large cluster that represented borrowers who are diligent to pay back the loan. On the other hand, several small clusters are identified which represents borrowers with high default probability and we also found these borrowers’ characteristics vary. We found no significant change in the structure of the cluster even when the aggregate amount of consumer credit was increased. Moreover, the expansionary monetary policy did not change the quantitative structure of household debt in Korea during the sample period. These results have implications for policymakers in terms of managing the potential risks associated with household debt.