Alternate Data Credit Scoring for the Underbanked in the Philippines

Alternate data credit scoring lets Philippine lenders assess underbanked and thin-file borrowers that bureau data alone cannot serve. By combining Credit Information Corporation (CIC) records with compliant non-bureau signals — bank and e-wallet cash flows, utility payments, and mobile behaviour — lenders can fairly score informal-sector workers and first-time borrowers instead of declining them by default.

Who Are the Underbanked in the Philippines?

The Philippines' financial-inclusion gap is large but narrowing. The World Bank's Global Findex 2021 found that around 51% of Filipino adults owned a financial account, leaving close to half outside the formal system — an estimated 9 million-plus adults unbanked. The Bangko Sentral ng Pilipinas (BSP) reports faster progress domestically: its 2021 Financial Inclusion Survey put account ownership at 56%, up sharply from 29% in 2019 — meaning roughly 44% of adults were still unbanked, often citing low income or lack of documents.

Many of these people are financially responsible — running sari-sari stores, driving for ride-hailing apps, receiving regular remittances, paying rent and electricity on time — yet carry little or no footprint at the CIC, the country's central credit registry. A sparse CIC report makes them look unscoreable.

This creates the "thin-file" borrower — creditworthy in practice but invisible to conventional scoring. Faced with an empty bureau report, a lender's instinct is to decline. But declining an unscoreable applicant is not declining a risky one; it is declining an unknown one. Within that unknown pool sits a large share of reliable borrowers who simply lack a formal record — and a real market a lender leaves to competitors. Micro, small and medium enterprises alone make up about 99.5% of Philippine businesses, many of them thin-file. See how AI scores thin-file borrowers.

What Is Alternate Data Credit Scoring?

Alternate data credit scoring uses financial signals that exist outside formal bureau reporting to assess creditworthiness. In a Philippine context, the most relevant and accessible signals include:

Bank and e-wallet cash flows. Income regularity, monthly surplus or deficit in Philippine pesos (₱), and consistent servicing of obligations — drawn from bank statements and digital wallet histories such as GCash or Maya, the richest alternate signal in a mobile-first economy.

Utility and telecom payments. On-time payment of electricity, water, and mobile-load bills is a steady proxy for meeting recurring obligations.

E-commerce and platform activity. For online sellers and gig workers, sales consistency and platform ratings evidence real, recurring income.

Employer or income tenure. Salary or receipts credited from the same source over time signal lower income-volatility risk.

None of these is used in isolation. Their value is in how they combine — with each other and with CIC data — to build a fuller borrower view. For deeper background, see alternate data sources for credit scoring and this alternate data credit scoring guide.

How Does Alternate Data Combine With CIC Data?

Alternate data does not replace the bureau — it complements it and fills the gap where the bureau is thin. A well-structured Philippine model works in layers.

Where a borrower has CIC history — or a score from an accredited credit bureau — it stays the primary input. Where it is thin or absent, the remaining layers carry more weight and still produce meaningful risk differentiation, where a bureau-only model would return nothing at all. This is how a lender distinguishes a borrower who is thin-file because they are financially fragile from one who is thin-file simply because they have never borrowed formally. The national ID system, PhilSys, further supports this by enabling electronic know-your-customer (eKYC) so first-time borrowers can be identified reliably at onboarding.

How AI Helps

YuALT is a no-code machine-learning platform that lets Philippine risk teams build, test, and deploy alternate-data credit models without a dedicated engineering team. It ingests bank-statement and e-wallet features, utility and telecom signals, and platform income alongside CIC data, engineers them into model-ready inputs, and produces an explainable score — with fairness testing so signals do not become proxies for gender, region, or other protected traits. Risk teams iterate models in days, not quarters, and every decision carries an audit trail for internal governance and regulatory review. The same alternate-data approach has supported over 10 million credit journeys across the YuVerse platform. The result: lenders responsibly extend credit to underbanked Filipinos who are creditworthy but invisible to bureau-only scoring.

Does Alternate Data Scoring Fit Philippine Regulation?

Any alternate-data model must rest on clear consent and conduct principles. Under the Data Privacy Act of 2012 (Republic Act No. 10173), enforced by the National Privacy Commission (NPC), borrowers must give informed consent to the data used, personal financial information is treated as sensitive, and only signals that are necessary and proportionate should be collected. Decisions must also be explainable to declined applicants and to compliance functions.

Sound affordability assessment still applies on top of the score. Collections conduct is separately governed: the Securities and Exchange Commission's Memorandum Circular No. 18, Series of 2019 prohibits unfair debt-collection practices. Widening access responsibly is exactly the aim of the BSP's National Strategy for Financial Inclusion 2022-2028, which prioritises inclusive digital finance and MSME credit. Fairness monitoring matters too: a model that leans on region or device data could disadvantage rural or lower-income applicants, so developers must test for and mitigate such effects. See how AI enables financial inclusion.

This is a general explainer, not legal or compliance advice.

FAQ

What does "underbanked" mean in the Philippines? It describes adults with little or no formal credit footprint at the CIC — often informal-sector workers, sari-sari store owners, gig earners, and first-time borrowers. They may be financially responsible but are hard to score with bureau data alone.

Does alternate data replace the CIC report? No. It complements the CIC. Where formal history exists, it remains the primary input. Alternate data fills the assessment gap for thin-file borrowers and adds depth for all applicants.

Which alternate signals work best in the Philippines? Bank and e-wallet cash flows, utility and telecom payment consistency, and platform income for online sellers are the most relevant and accessible. They are combined with CIC data rather than used alone.

Is alternate data credit scoring compliant with Philippine rules? It must be built on informed consent, data minimisation, explainability, and fairness monitoring under the Data Privacy Act of 2012, and operate within BSP and SEC consumer-protection expectations. Implementations should be reviewed by qualified legal and compliance professionals.

How does this avoid unfair bias? Through fairness testing that checks whether signals act as proxies for protected characteristics such as gender or region. A responsible model flags and mitigates these effects before deployment and keeps an explainable audit trail.

Which Philippine lenders benefit most? Digital banks, fintech and lending companies, rural banks, and MSME-focused lenders targeting informal and first-time-borrower segments. Any lender with a high share of thin-file applications faces a choice between systematic exclusion and responsible alternate assessment.

Conclusion

In a market where a large share of adults still sits outside the formal financial system, bureau-only scoring leaves many creditworthy Filipinos unscored. Alternate data credit scoring closes that gap — combining CIC records with cash-flow, e-wallet, utility, and platform signals to assess the underbanked fairly, within Data Privacy Act, BSP, and SEC rules. Explore how YuVerse scores thin-file borrowers responsibly with YuALT.

Score the underbanked responsibly. Talk to the YuVerse team

References

• World Bank, Global Findex Database 2021 — Account Ownership — https://www.worldbank.org/en/publication/globalfindex/brief/the-global-findex-database-2021-chapter-1-ownership-of-accounts
• Bangko Sentral ng Pilipinas, 2021 Financial Inclusion Survey — Topline Report — https://www.bsp.gov.ph/Inclusive%20Finance/Financial%20Inclusion%20Reports%20and%20Publications/2021/2021FISToplineReport.pdf
• Bangko Sentral ng Pilipinas, National Strategy for Financial Inclusion 2022-2028 — https://www.bsp.gov.ph/Pages/InclusiveFinance/NSFI-2022-2028.pdf
• National Privacy Commission, Republic Act No. 10173 — Data Privacy Act of 2012 — https://privacy.gov.ph/data-privacy-act/
• Securities and Exchange Commission, Memorandum Circular No. 18, Series of 2019 — https://lpr.adb.org/resource/prohibition-unfair-debt-collection-practices-financing-companies-and-lending-companies