How Sella Delivers Scalable Credit Risk Explanations with Prometheux

Overview

Founded in 1886, Sella is one of the largest private and independent banking groups in Italy, with over 300 branches serving 1.4+ million customers and a well-established reputation for innovation.

Managing complex data from retail to corporate clients, Sella operates specialized risk desks across offices to support sophisticated analysis and client management. Specifically, the credit rating team computes monthly credit scores for all clients, feeding into a risk framework for provisioning, compliance, and decision-making.

Rating changes trigger inquiries from branches, requiring analysts to manually retrieve data, compare outputs, and craft concise, precise explanations. This process was largely manual and not scalable.

Sella chose Prometheux to automate this process—cutting response time by 99% per case on average, from up to 17 minutes per case to 5 seconds for even millions of cases processed in parallel—unlocking a world of new agentic applications.

The Challenge

As Sella's workflows matured, the credit rating team reached a familiar breaking point for many data-driven financial institutions: manual analysis became unsustainable with millions of clients.

The process for explaining credit rating changes to branch managers was manual and time consuming:

• Up to 17 minutes per case
• One case at a time
• Complex Excel workflows with many interdependent variables
• Manual cross-referencing across multiple files
• Manual, time-consuming what-if analysis

"The process was entirely manual: the branch manager opened a request via a portal and we manually explained why a rating changed. Many requests for very small amounts but very limited reporting and tools to make relationship managers autonomous."

Massimiliano Malin
Head of Credit Risk

"[In previous attempts for a different model with similar requirements] it took a team of 4-5 people about 1.5 years, alongside their other responsibilities, to create a dashboard in Power BI which did not even provide an explanation in natural language, let alone a personalized one."

Vincenzo Cecere
Credit Risk Analyst, Sella

The Solution

With Prometheux, Sella reduced the credit rating analysis time from up to 17 minutes per case to 5 seconds for even millions of cases processed in parallel.

Sella's credit risk team used Prometheux to transform the slow, manual process into a scalable and intelligent one, by seamlessly connecting to customer data, translating convoluted Excel workflows into simple logic and connecting to LLMs for explanations in natural language.

"Prometheux enabled us to build a system that can access our databases, process all the client's historical variables, and provide an intelligent, understandable explanation autonomously."

Massimiliano Malin
Head of Credit Risk, Sella

Part of what made Prometheux the right fit was its ability to ground AI in explainable data processing and its ability to effortlessly scale to millions of analyses simultaneously.

Sella now powers real-time credit rating analysis, automatically identifying critical variables, generating explanatory comments in natural language as well as what-if simulations, all with end-to-end data lineage.

"Personalization is essential in our explanations to build trust—generic text would undermine credibility. We are automating something that actually needs to be as personal as possible."

Vincenzo Cecere
Credit Risk Analyst, Sella

"Nothing comparable to what we did manually, this is excellent. We literally spent hours doing this by hand, this is great."

Laura Tomassini
Credit Risk Analyst, Sella

Looking Ahead

With Prometheux as data foundation layer for both humans and AI, Sella is ready to scale success across the organization by continuing to evolve from manual, reactive workflows to proactive, intelligent ones, embedded across its digital ecosystem.

Expanding to more teams, capturing more domain logic from the heads of experts and making it simply executable, auditable, and reusable in real time, Sella is unlocking an entirely new class of agentic applications — systems that can:

• Help prevent issues before they occur
• Trigger alerts e.g. "pay your rent to avoid a rating drop"
• Proactively simulate what-if scenarios
• Support instant decision-making for both branch managers and end users

Specialized teams can now translate their domain expertise into structured modules of deep domain knowledge, powering transparency, automation, and intelligent services across the organization, empowering the future of banking.