Business Optimisation

Pricing, Scoring, Rating using Machine Learning

Pricing, Scoring, Rating using Machine Learning

The credit spread is required for the credit application process. The credit spread should take into account the expected credit loss for an individual deal. As an alternative to conventional methods of scoring, rating and PD determination, Machine Learning can also be used, for this purpose, on the basis of a performance database filled with Deep Learning.

FlexFinance provides an API that can be integrated into the credit application process. We have other solutions for credit monitoring, accounting and backtesting.

Improve pwECL using Machine Learning

The most significant impact on overall bank management is caused by the introduction of the Expected Credit Loss approach to reflect credit risk in external accounting.

IFRS 9 calls for the segmentation of financial assets on the basis of similar credit risk characteristics. For each segment, the expected credit loss needs to be calculated taking probability-weighted macroeconomic scenarios into account.

In contrast to the conventional segmentation/portfolio formation of loans, FlexFinance offers the ECL calculation on the basis of machine learning.

Improve pwECL using Machine Learning
Loan Monitoring, Early Warning using Machine Learning

Loan Monitoring, Early Warning using Machine Learning

The application monitors the loans for which contracts already exist. Not only are customers and contract data taken into account, but macro- and microeconomic factors that naturally influence credit management are also considered. Based on deep learning processes and machine learning, the EWS application identifies criteria that point to an adverse business situation.

The EWS application initiates a workflow when certain events occur. The events could also be the variance of the ECL, for example. The workflow actions could also be linked to contract deadlines in such a way that realistic options for action exist.

White Paper "AI solutions in the banking environment"

Artificial intelligence, or AI for short, is currently on everyone’s lips. We associate buzzwords such as machine learning, neural networks and self-learning algorithms with a modern trend technology that we already encounter all too often in everyday life: Be it voice assistants like Alexa, Siri, Cortana & Co, personalised advertising while surfing the internet, traffic jam reports from Google Maps or sense-based translation tools like DeepL.
But what about the use of AI solutions in the banking environment?

White Paper "AI solutions in the banking environment"
How secure are your recurring incoming payments?

How secure are your recurring incoming payments?

Our AI knows the answer!
More and more companies are relying on business models with recurring payments in the form of subscriptions, instalment payments and the like. Defaults and/or delays in these payment flows often represent a considerable economic risk for the respective provider. Artificial intelligence (AI) has also found its way into the financial sector. FERNBACH has used AI to develop a solution that can be used to forecast the future payment behaviour of customers in arrears.

Artificial intelligence – best practice guidelines

We can show you how to implement a project for artificial intelligence without a security risk when the AI application is operated via a remote connection. Based on practical experience, we have developed a simple procedure model that can be easily used in a bank. Even without any knowledge of artificial intelligence and complex software development.

Artificial intelligence – best practice guidelines