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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The goal of our 4-phase research project was to test if amachine-learning-based loan screening application (5D) could detect bad loanssubject to the following constraints: a) utilize a minimal-optimal number offeatures unrelated to the credit history, gender, race or ethnicity of theborrower (BiMOPT features); b) comply with the European Banking Authority andEU Commission principles on trustworthy Artificial Intelligence (AI). Alldatasets have been anonymized and pseudoanonymized. In Phase 0 we selected asubset of 10 BiMOPT features out of a total of 84 features; in Phase I wetrained 5D to detect bad loans in a historical dataset extracted from amandatory report to the Bank of Italy consisting of 7,289 non-performing loans(NPLs) closed in the period 2010-2021; in Phase II we assessed the baselineperformance of 5D on a distinct validation dataset consisting of an activeportolio of 63,763 outstanding loans (performing and non-performing) for atotal financed value of over EUR 11.5 billion as of December 31, 2021; in PhaseIII we will monitor the baseline performance for a period of 5 years (2023-27)to assess the prospective real-world bias-mitigation and performance of the 5Dsystem and its utility in credit and fintech institutions. At baseline, 5Dcorrectly detected 1,461 bad loans out of a total of 1,613 (Sensitivity = 0.91,Prevalence = 0.0253;, Positive Predictive Value = 0.19), and correctlyclassified 55,866 out of the other 62,150 exposures (Specificity = 0.90,Negative Predictive Value = 0.997). Our preliminary results support thehypothesis that Big Data & Advanced Analytics applications based on AI canmitigate bias and improve consumer protection in the loan screening processwithout compromising the efficacy of the credit risk assessment. Furthervalidation is required to assess the prospective performance and utility of 5Din credit and fintech institutions.

Baseline validation of a bias-mitigated loan screening model based on  the European Banking Authority's trust elements of Big Data & Advanced  Analytics applications using Artificial Intelligence