Case Studies

A major bank wanted to grow its SME lending business within its risk appetite. With 100,000 SME borrowers, it had scale and data, but too many decisions still depended on manual underwriting, slowing response times and limiting growth.

The bank had two clear goals:
1. Shift more underwriting decisions from manual review to automated decisioning, shortening underwriting time and improving customer response times
2. Increase the number of customers who could be approved automatically, while also increasing approval amounts where justified.

​

The Challenge

Like many banks, the institution relied on manual underwriting, and partially on traditional models and rules that worked well, but were less effective across the full diversity of SME profiles. As a result, strong borrowers outside legacy segments were harder to identify, many cases were sent to manual review, and approval opportunities were missed.

The bank needed a solution that could improve decision quality, expand automation, and remain auditable, and practical for a regulated environment.

​

The Solution

The bank deployed pert.AI within its existing data environment to optimize SME lending decisions.

pert.AI integrated diverse data sources, analyzed historical decisions and outcomes, and identified patterns missed by conventional models and business rules. This enabled the bank to move beyond static segmentation and make more precise automated decisions.

With pert.AI, the bank was able to:

• Move more cases from manual underwriting to automated decision flows

• Shorten underwriting turnaround times and improve customer response speed

• Approve more eligible SME customers automatically

• Increase approval amounts within borrower quality and risk profile

​​

The Results

+24% Automatic approvals

+17% Credit growth

Improved credit segmentation
Sharper identification of borrower quality and opportunity

8 weeks Time to value

​

Why It Matters

In SME lending, growth is often limited not by demand, but by rigid decision systems and heavy reliance on manual underwriting. This case shows how pert.AI helps banks automate more decisions, respond faster to customers, and unlock additional credit growth with greater precision and control.