A new perspective of credit scoring for small and medium-sized enterprises based on invoice data

Abstract

Credit Scoring takes a prominent part in the finance of small and medium-sized enterprises (SMEs), and it is also an invaluable tool to predict credit default. However, due to the variety of market size, capital scale, and the limitations of Credit Scoring Model, it is difficult for SMEs to refer to large enterprises for Credit Scoring. And as an important reference, financial statements are insufficient and time window is inflexible, which would fail to make data reflect the enterprise's operating conditions correctly and timely, inaccurate credit prediction arising. Therefore, we offer an inspiring perspective to search elastic and time-independent evidence. Served as an indispensable basis of accounting in China, invoices take full notes on taxes of economic business, with more details about financial statements and more flexibility over periods, which can develop a sustainable approach to master the operation information of SMEs in time. To deal with invoice data of SMEs, we study influential variables under the first digit law inspired by Benford's law, apply machine learning techniques, and guide experiment by the construction of score card. It shows that our method formed by easy-to-accomplish steps is of applicability and effectiveness, to support powerfully the existing Credit Scoring system.