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

Machine learning plays an essential role in preventing financial losses inthe banking industry. Perhaps the most pertinent prediction task that canresult in billions of dollars in losses each year is the assessment of creditrisk (i.e., the risk of default on debt). Today, much of the gains from machinelearning to predict credit risk are driven by gradient boosted decision treemodels. However, these gains begin to plateau without the addition of expensivenew data sources or highly engineered features. In this paper, we present ourattempts to create a novel approach to assessing credit risk using deeplearning that does not rely on new model inputs. We propose a new credit cardtransaction sampling technique to use with deep recurrent and causalconvolution-based neural networks that exploits long historical sequences offinancial data without costly resource requirements. We show that oursequential deep learning approach using a temporal convolutional networkoutperformed the benchmark non-sequential tree-based model, achievingsignificant financial savings and earlier detection of credit risk. We alsodemonstrate the potential for our approach to be used in a productionenvironment, where our sampling technique allows for sequences to be storedefficiently in memory and used for fast online learning and inference.

Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data