A loan officer who sees the street before she lends

The challenge

Every application comes with a story, and she cannot visit every street. Some shops have already closed by the time the money lands. Others sit on a street with five copies of the same shop. Last year one in six of her loans went bad.

How the flow works

With xMap Flows, Thandi built Streetwise. Streetwise is an AI employee: a flow of 6 blocks.

1. When a new loan application comes in,

   A new application (New rows)

2. Streetwise finds the shop on the map and checks it is open,

   The shop itself (Map business scan)

3. counts the same kind of shop within five hundred metres,

   Rivals on the street (Nearby places)

4. judges how likely the shop is to keep trading,

   Will the street carry it? (Jev decision)

5. asks Thandi to approve,

   Thandi has the last word (Approval)

6. and sends the owner the answer on WhatsApp.

   The answer, to the owner (WhatsApp Business)

What it solves

• Can’t visit every street: solved by Map business scan and Nearby places
• Shops closed already: solved by Map business scan
• Five rivals next door: solved by Nearby places and Jev decision

The result

This week, Streetwise checked thirty applications in an hour. Two shops had already closed, and one salon had seven others within a short walk. Thandi spent her afternoons with the strongest twenty, and gave each an answer the same day.

Thandi still trusts her instinct. Now the street backs it up.

An illustrative scenario: the figures are modelled to show what the flow produces, not a customer's results.

The flow, block by block

1. 1

   A new application

   New rows

   Starts the flow when new rows appear in a Google Sheet or in a table in My data.

2. 2

   The shop itself

   Map business scan

   Finds businesses on online maps live: name, category, rating, address, phone, website and whether it is open.

3. 3

   Rivals on the street

   Nearby places

   Places around a point from xMap’s own places database (300M+ places, refreshed every month): pick the types of place (more than 5,000, such as Restaurant, Cafe, Pharmacy, Hospital or Gas station, or a whole group of them) and how far to look.

4. 4

   Will the street carry it?

   Jev decision

   Asks TypeSafe’s Jev model one typed question about each place: yes or no, pick one of your options, or a score on your levels.

5. 5

   Thandi has the last word

   Approval

   Stops the run until someone says yes.

6. 6

   The answer, to the owner

   WhatsApp Business · WhatsApp

   Send text, media and template messages from your WhatsApp Business number.

Templates to build it

Ready-made flows with the same blocks. Open one, change the city and the kind of place, and run it.

• Check new merchants from my sheetNew merchants checked on the map, with a risk level.
• Tyre shops in mining towns, for OTR tyre salesTyre and truck shops graded as off-the-road tyre dealers.
• What opened in my patch, on WhatsApp to my buyersWhat opened in your patch this week, written up as a short update, approved by you, then sent to your buyers on WhatsApp.
• Independent phone shops to recruit as dealersIndependent phone shops to recruit as dealers, sent to the nearest territory manager.
• Truck repair and machine shops for my spare parts repsNew workshops graded as spare parts buyers, to the reps.
• Independent gyms for my membership softwareIndependent gyms graded as software customers, to the sales team.

Industries

Learn how it works

• POI data (points of interest)Records of places such as shops, clinics and offices, with their category, position and details.
• Outlet universeThe complete list of points of sale a brand could sell through.
• Location intelligenceUsing where things are, and what is around them, to make business decisions.
• The xMap Flows browser extension: what is around this businessOn a company’s website or a place on a map, one click shows its market and the AI employees to hire for it.
• Build your first flow in ten minutesFrom a blank page to a flow that emails you a ranked list every morning.
• What xMap remembers about your companyYour city, industry and what you sell, filled in for you and always yours to change.

More stories from Banking & fintech

• The credit committee starts every week on fresh salesOmar heads mortgage risk at one of Riyadh’s largest banks. His team signs off on thousands of home loans a year.
• Cash machines that follow the street, not last yearMei runs the cash machine network for one of Shanghai’s largest banks. Her team looks after four hundred machines across the city.
• Trouble at a borrower, read the same morningEthan leads credit monitoring for small business loans at a big Chicago bank. His team watches over two thousand borrowers.
• New money agents where people already gatherGrace leads agent growth at a mobile money company in Kigali. Its agents are the corner shops where people put cash in and take it out.

All 137 stories →