Publication Details
Abstract
This article develops and empirically tests an integrated data-driven framework for corporate creditworthiness assessment. The proposed framework, named FinTech-Based Corporate Credit Assessment Framework (FT-CCAF), combines internal bank data, credit bureau records, tax authority information, pledge registry data, sectoral benchmarks, transactional cash-flow indicators and explainable artificial intelligence. The framework is designed for emerging and bank-based financial systems where corporate lending still relies heavily on documents supplied by the borrower and on relationship-based judgement. The empirical base is a pilot implementation in a commercial bank in Uzbekistan, used here not as a local case description, but as a test environment for a transferable methodology. The study applies a pre/post quasi-experimental design, two-proportion tests, chi-square statistics and comparison of analytical preparation time. The results indicate that integrated official data and automated financial analytics can materially improve early risk detection, reduce calculation errors and shorten the corporate lending cycle while preserving the role of underwriters and credit committees. The proposed model can be adapted by banks in other emerging markets if equivalent public registries, credit bureau records and digital consent mechanisms are available.