Assessing Skip-Tracing Information in Repossession Prediction Using Ensemble Learning and SHAP Analysis

Predictive modeling for auto-repossession risk has received little academic attention despite its operational importance. When a vehicle cannot be located, repossession companies often rely on skip-tracing, an established industry practice that uses third-party data sources such as license plate rec...

Täydet tiedot

Bibliografiset tiedot

Päätekijät:	Andy Sinclair, Preston Billion-Polak, Taghi M. Khoshgoftaar
Aineistotyyppi:	Artigo
Kieli:	Inglês
Julkaistu:	IEEE 2026-01-01
Sarja:	IEEE Access
Aiheet:	Auto repossession prediction skip-tracing data imbalanced classification ensemble learning model explainability (SHAP)
Linkit:	https://ieeexplore.ieee.org/document/11589248/
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!