A fresh take on risk and valuation
Back to all services

Credit Risk Modelling

The highest possible predictive power of your models
Designed to help Credit Risk Modelling Units
Bank’s competitive advantage to a great extent depends on modernity of models in use. Finalyse offers support in methodology choices, the development of scoring models for credit decisioning and monitoring purposes and their deployment. These models are built with respect for industry-leading methods, including Machine Learning techniques.

How does Finalyse address your challenges?

We take accountability for the entire model development process – starting from data preparation through exploratory data analysis and ending with model development and its validation on independent sample.

Holding true for all recommendations from European and local authorities, we guarantee the regulatory compliance of the model developed.

Control your model risk with Finalyse Credit Risk Modelling toolkit to bridge the talent gap and reduce implementation risks. 

Get all your questions answered

How does it work in practice?

Key Features

  1. A model developed to fit your needs. Having completed numerous model development projects for all kinds of institutions across Europe, Finalyse leverages on its vast experience and tailors the offer to each individual client.
  2. Finalyse Machine Learning Model Validation  Framework will help to ensure that your model performs as expected.

What Finalyse experts say

01 Feb, 2018
IFRS 9 Expected Loss Model Validation

This expert input focuses on the validation of Expected Credit loss model validation; more specifically, it explains why it is a good idea now, after the scramble to have IFRS 9 compliant models in time, to consider validation. This input addresses the challenges of a methodological review of all models, and more specifically, it addresses the review of selected variables – macroeconomic factors, obligor characteristics, etc. It shows how to make the best use of the new ability to compare the outcomes of the models against the observed losses. In addition, this article tackles another challenge: the review of data quality – particularly of the modelling data set and new data.

17 Sep, 2020
Behavioral Scorecard with Machine Learning Components

This article discusses the benefits of applying advanced analytics in the development of behavioural scoring models. It investigates how Machine Learning techniques can be used to model the behavioural scores of consumers in each step of the development and model assessment. Some concerns regarding the usage of Machine Learning in behavioural scoring models are addressed.