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

Rapid development of advanced modelling techniques gives an opportunity todevelop tools that are more and more accurate. However as usually, everythingcomes with a price and in this case, the price to pay is to looseinterpretability of a model while gaining on its accuracy and precision. Formanagers to control and effectively manage credit risk and for regulators to beconvinced with model quality the price to pay is too high. In this paper, weshow how to take credit scoring analytics in to the next level, namely wepresent comparison of various predictive models (logistic regression, logisticregression with weight of evidence transformations and modern artificialintelligence algorithms) and show that advanced tree based models give bestresults in prediction of client default. What is even more important andvaluable we also show how to boost advanced models using techniques which allowto interpret them and made them more accessible for credit risk practitioners,resolving the crucial obstacle in widespread deployment of more complex, 'blackbox' models like random forests, gradient boosted or extreme gradient boostedtrees. All this will be shown on the large dataset obtained from the PolishCredit Bureau to which all the banks and most of the lending companies in thecountry do report the credit files. In this paper the data from lendingcompanies were used. The paper then compares state of the art best practices incredit risk modelling with new advanced modern statistical tools boosted by thelatest developments in the field of interpretability and explainability ofartificial intelligence algorithms. We believe that this is a valuablecontribution when it comes to presentation of different modelling tools butwhat is even more important it is showing which methods might be used to getinsight and understanding of AI methods in credit risk context.

Enabling Machine Learning Algorithms for Credit Scoring -- Explainable  Artificial Intelligence (XAI) methods for clear understanding complex  predictive models