How Voice AI Automates Personal Loans Collections for Lenders in Vietnam
Voice AI automates personal loans collections in Vietnam by placing consistent, empathetic Vietnamese reminder calls at scale, confirming monthly instalment amounts in đồng, capturing promises-to-pay, and escalating hardship cases to humans. It lifts contact rates in early buckets while respecting State Bank of Vietnam (SBV) consumer-finance conduct rules and personal-data law.
Unsecured personal lending is one of Vietnam's most competitive segments. Three companies — FE Credit, HD Saison, and Home Credit — dominate roughly 80% of the consumer-finance market (Vietnam News), and thin margins make cost-to-collect a decisive factor. Voice AI — automated agents that call, remind, negotiate simple arrangements, and escalate — helps lenders recover more from small-ticket personal loans without adding headcount or breaching conduct rules.
Why Are Personal Loan Collections So Hard in Vietnam?
Personal loans are high-volume and low-value, so the cost of chasing each account matters enormously. A manual tele-caller spends most of the day on unanswered calls and wrong numbers rather than live conversations.
Three pressures stand out:
Volume overwhelms manual teams. A single portfolio can hold hundreds of thousands of accounts across 1–30 and 31–60 Days Past Due (DPD) buckets — far more than agents can dial by hand.
Early buckets get under-served. Most recoverable value sits in the first two buckets, but teams often crowd around hard, late accounts and miss the cheap wins.
Inconsistency creates compliance risk. Under target pressure, human agents may drift from approved language — precisely the behaviour SBV conduct rules restrict.
What SBV Rules Govern Personal Loan Collections?
Vietnam regulates how finance companies pursue overdue consumer loans. Circular 43/2016/TT-NHNN, as amended by Circular 18/2019/TT-NHNN, directs how debt reminders must be conducted — capping reminder calls at a maximum of five per day, restricting them to permitted daytime hours, and prohibiting threats, coercion, and pressure on people who are not the borrower (Circular 18/2019/TT-NHNN, LuatVietnam). Borrower data must be processed lawfully under Decree 13/2023/ND-CP and the 2025 Personal Data Protection Law. This is an explainer, not legal advice.
Requirement area | What it means for personal loan collections |
|---|---|
Call frequency | No more than five reminder calls per day per borrower |
Timing | Contact only within permitted daytime hours |
Conduct | No threats, insults, coercion, or reputation-damaging tactics |
Third parties | Do not pressure relatives, colleagues, or references |
Data | Process borrower data lawfully under Decree 13/2023/ND-CP |
Voice AI has a structural advantage here: every call follows an approved script within configured windows and is fully logged, so compliance is enforced by design rather than left to individual agent discipline.
How Does Voice AI Automate the Collections Flow?
Contact rates rise. Automated agents dial thousands of accounts in parallel at the best-answer times, so more calls connect and reach a live conversation.
Early buckets get blanket coverage. Cheap, high-frequency reminders cover 1–30 and 31–60 DPD accounts before balances harden — the early-bucket resolution approach proven at scale.
Conversations stay compliant. Every call uses approved, non-coercive Vietnamese, capped at the permitted frequency:
"Xin chào anh/chị, đây là lời nhắc thân thiện về khoản trả góp vay tiêu dùng đến hạn vào [DATE] với số tiền [AMOUNT] ₫. Anh/chị có thể thanh toán trước ngày đến hạn không ạ?" ("Hello, this is a friendly reminder about your personal-loan instalment of [AMOUNT] ₫ due on [DATE]. Can you pay before the due date?")
Promises-to-pay are captured. The agent records commitments in đồng and schedules automated follow-ups, improving promise-to-pay rates without extra staff.
Humans focus where they matter. Distressed or disputed accounts route to trained agents with full context, following the same outbound-collections model used across markets.
How AI Helps
YuVoice runs early- and mid-bucket personal-loan collections as automated Vietnamese voice conversations — reminding, confirming instalment amounts in đồng, capturing promises-to-pay, and escalating hardship cases to humans with full context. Every call stays inside configured time windows, respects the five-call-per-day cap, uses approved non-coercive language, and is transcribed for audit against SBV conduct rules and Vietnam's data-protection law. Handling over 25 million calls a month across financial-services deployments, it gives lenders elastic capacity at Tết and month-end peaks without adding agents — improving contact and recovery rates while keeping collections consistent, humane, and fully logged.
FAQ
Is it legal to use voice AI for personal loan collections in Vietnam? There is no ban on automated reminders. AI agents must operate within the conduct rules that apply to all collections under Circular 43/2016/TT-NHNN (as amended) — the five-call-per-day cap, permitted hours, no coercion, and lawful data handling. This is an explainer, not legal advice.
Which buckets suit voice AI best? Early buckets — 1–30 and 31–60 DPD — where borrowers respond to a polite reminder and recovery is cheapest. Late-stage, disputed, or hardship accounts route to human specialists.
Can AI handle borrowers who say they cannot pay? Yes. It acknowledges hardship, offers configured options such as a revised date, and escalates to a human for anything needing judgment — never pressuring or threatening.
Does it work for finance companies as well as banks? Yes. Consumer-finance companies, which hold much of Vietnam's unsecured personal lending, use the same early-bucket reminder and promise-to-pay flows tuned to their products.
How does AI respect the call-frequency limit? Per-account frequency caps and calling windows are configured centrally, so the system cannot dial over the five-call daily limit or outside permitted hours.
What record is kept of each call? Every call is transcribed and time-stamped, giving a complete, auditable record that supports both SBV oversight and internal quality assurance.
Conclusion
Voice AI lets Vietnamese lenders automate the high-volume, low-value work of personal loan collections — reaching more borrowers in the buckets that matter, capturing promises-to-pay, and making compliance the default. By scaling empathetic, script-consistent Vietnamese reminders inside SBV's conduct rules and logging everything, banks and finance companies cut cost-to-collect and protect their reputation.
Automate personal loan collections, compliantly, at scale. Talk to the YuVerse team to see voice AI built for Vietnam.
References
- Vietnam News — Three companies dominate consumer lending market in VN — https://vietnamnews.vn/economy/898552/three-companies-dominate-consumer-lending-market-in-vn.html
- Circular 18/2019/TT-NHNN amending Circular 43/2016/TT-NHNN on consumer lending (LuatVietnam) — https://english.luatvietnam.vn/circular-no-18-2019-tt-nhnn-dated-november-04-2019-of-the-state-bank-of-vietnam-on-amending-supplementing-some-articles-of-the-circular-no-43-2016-178364-doc1.html
- Decree No. 13/2023/ND-CP on protection of personal data (LuatVietnam) — https://english.luatvietnam.vn/decree-no-13-2023-nd-cp-dated-april-17-2023-of-the-government-on-personal-data-protection-249791-doc1.html
- State Bank of Vietnam (SBV) — https://www.sbv.gov.vn
