Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Vaya: an AI loan advisor that asks whether you can still afford to live

Description and use

Vaya is an AI loan advisor that tells you whether you can still afford to live after taking a loan, using Monte Carlo simulations and real bank data. It compares 20+ Vietnamese banks, shows risk scores, offers actionable suggestions, and includes a reverse‑auction marketplace.

Problem

Loan comparison sites focus only on lowest rates, ignoring whether a loan is affordable for the borrower.

Outcome

Vaya enables borrowers to assess loan affordability quickly, providing transparent comparisons, risk scores, and actionable guidance, while also offering a reverse‑auction marketplace for better deals.

Workflow

  • 1. User enters a one‑sentence description of their loan and income in the chat input.
  • 2. Vaya fetches real product data from 20+ Vietnamese banks (rates, limits, terms, LTV, processing time).
  • 3. It runs a client‑side Monte Carlo simulation of income, expenses, and existing debt to compute a survival probability and key ratios (DTI, PTI, LTV, disposable income).
  • 4. Results are displayed in sortable tables, interactive charts, and a survival score with plain‑language explanations.
  • 5. If a loan is risky, Vaya suggests adjustments (lower amount, longer term, higher down payment, expense cuts).
  • 6. Users can post an anonymous request to a reverse‑auction marketplace where banks bid based on the request details.
  • 7. All interactions are multilingual (English, Vietnamese, Chinese) and available in dark mode.

Evidence

Vaya runs a Monte Carlo simulation over your income, expenses and existing debt, and tells you the probability that the loan pushes you underwater — plus DTI, PTI, LTV and disposable income, each with a plain‑language explanation attached.

Source

It compares real products from 20+ Vietnamese banks. Rates, maximum amounts, terms, processing time, LTV caps — side by side, sortable, filterable, with the actual bank logos so you know who you are dealing with.

Source

  • Record date: 2026-09-10T07:00:43.364Z