English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Credit assessments activities are essential for financial institutions andallow the global economy to grow. Building robust, solid and accurate modelsthat estimate the probability of a default of a company is mandatory for creditinsurance companies, moreover when it comes to bridging the trade finance gap.Automating the risk assessment process will allow credit risk experts to reducetheir workload and focus on the critical and complex cases, as well as toimprove the loan approval process by reducing the time to process theapplication. The recent developments in Artificial Intelligence are offeringnew powerful opportunities. However, most AI techniques are labelled asblackbox models due to their lack of explainability. For both users andregulators, in order to deploy such technologies at scale, being able tounderstand the model logic is a must to grant accurate and ethical decisionmaking. In this study, we focus on companies credit scoring and we benchmarkdifferent machine learning models. The aim is to build a model to predictwhether a company will experience financial problems in a given time horizon.We address the black box problem using eXplainable Artificial Techniques inparticular, post-hoc explanations using SHapley Additive exPlanations. We bringlight by providing an expert-aligned feature relevance score highlighting thedisagreement between a credit risk expert and a model feature attributionexplanation in order to better quantify the convergence towards a betterhuman-aligned decision making.

Explaining Credit Risk Scoring through Feature Contribution Alignment with Expert Risk Analysts