Cash Flow Underwriting with Bank Transaction Data: Advancing MSME Financial Inclusion in Malaysia

Paper: arXiv 2510.16066

Authors: Chun Chet Ng, Wei Zeng Low, Jia Yu Lim, Yin Yin Boon

Abstract

Despite accounting for 96.1% of all businesses in Malaysia, access to financing remains one of the most persistent challenges faced by Micro, Small, and Medium Enterprises (MSMEs). Newly established businesses are often excluded from formal credit markets as traditional underwriting approaches rely heavily on credit bureau data. This study investigates the potential of bank statement data as an alternative data source for credit assessment to promote financial inclusion in emerging markets. First, we propose a cash flow-based underwriting pipeline where we utilise bank statement data for end-to-end data extraction and machine learning credit scoring. Second, we introduce a novel dataset of 611 loan applicants from a Malaysian lending institution. Third, we develop and evaluate credit scoring models based on application information and bank transaction-derived features. Empirical results show that the use of such data boosts the performance of all models on our dataset, which can improve credit scoring for new-to-lending MSMEs. Finally, we will release the anonymised bank transaction dataset to facilitate further research on MSME financial inclusion within Malaysia’s emerging economy.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper employs standard machine learning models (e.g., Logistic Regression, Random Forest) and an agentic workflow without novel mathematical derivations or heavy quantitative modeling. However, it demonstrates strong empirical rigor by introducing a novel real-world dataset of 611 loan applicants, detailing an end-to-end implementation pipeline with specific modules, and providing evaluation results.

Research Flowchart

  flowchart TD
  Start["Research Goal:<br/>Assess bank transaction data for<br/>MSME credit scoring in Malaysia"] --> Inputs["Data Input:<br/>Novel dataset of 611 MSME loan applicants<br/>with bank statements & application info"]
  Inputs --> Features["Feature Engineering:<br/>Extract cash flow metrics &<br/>traditional application features"]
  Features --> Modeling["Computational Process:<br/>Develop & evaluate ML<br/>credit scoring models"]
  Modeling --> Results["Key Findings:<br/>Transaction data significantly<br/>improves model performance"]
  Results --> Outcome["Outcome:<br/>Enables credit scoring for<br/>new-to-lending MSMEs &<br/>release of anonymized dataset"]

Cited References (60)

1. Enabling a More Relevant, Efficient and Diversified Market (2025) — link
2. Cover Story: Closing the RM90 bil MSME funding gap (2024) — link
3. The Use of Alternative Data in Credit Risk Assessment: Opportunities, Risks, and Challenges (2024) — link
4. EXPRESS: Who Benefits from Alternative Data for Credit Scoring? Evidence from Peru (0) — link
5. How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm (2024) — link
6. CRISP-DM 1.0 Step-by-step data mining guide (2000) — link
7. Intelligent credit scoring: Building and implementing better credit risk scorecards (2017)
8. Building a Cash Flow Underwriting System: Insights from Implementation (2024)

0 of 60 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.