The new application form brought in +$2M in 2025
Cut the microloan application form from 8 minutes to 2: the user just snaps their passport and a selfie, and we issue a loan of up to $500.
Context
Alfa-Money — microloans up to $500 on your card in 5 minutes. There were two steps: first the user filled in their name and contacts, then passport details by hand.
What problems we found
Goals
Discovery
Previously we only knew the overall drop-off number. We didn't know where exactly people quit, or why. So we went digging.
MFO customers are a specific audience: students, people in debt, gamblers. Urgency outweighs privacy for them — a passport photo reads as a fair trade for getting the money fast.
User flow
We learned that the «marital status» and «education» fields didn't improve approval accuracy — their contribution to default prediction turned out to be statistically insignificant. Combined with user feedback from interviews, we dropped them. The loan itself is issued in the authorized zone — inside the bank's app.
Fills in name, last name and contacts
Types passport details by hand
Fills in personal data
Gets approval or rejection
Snaps passport, address and a selfie
Reviews recognized data and ticks the consent boxes
Gets approval or rejection
Hypotheses
If we remove manual entry of passport fields and replace it with a photo — conversion to submission will grow
Variant B won: submission CR higher by
+ 18 pp
If we tell the user what's happening during scoring — they won't close the tab
Drop-off at scoring decreased by
−12 pp
If we add a button that opens the app and an animated visual for the approved amount — take rate will grow by ~10–15%
Take rate grew by
+ 8 pp
Rejected ideas
Not everything we discussed made it into the MVP. Some ideas we rejected outright, some we parked in the backlog — here are the most telling ones.
It opens a fraud hole — someone could submit a stranger's passport found online. With an in-app camera, we know the photo was taken here and now.
More expensive to integrate, slower for the user. The level of protection is comparable to a liveness photo.
Post-analysis and takeaways
After release we collected metrics for 2 months. An A/B test: 50% of traffic on the new flow, 50% on the old form. The test group clearly beat the control, and the flow was rolled out to 100%.
What I learned along the way
- 1.18% use the edit mode for recognized fields — without it, we'd be fielding complaints about “it recognized this wrong.”
- 2.It matters to give users a choice — fill via passport or by hand. There are cases when the passport isn't nearby but the person remembers the details by heart; without the alternative, that user just drops off. This is going into the Q2 2026 follow-up.