Search Results - subject:"model interpretability"

Forecasting China bond default with severe class-imbalanced data : a simple learning model with causal inference

Peng, Mike W.; Stern, Elisheva R.; Hu, Hanwen - In: Economic modelling 144 (2025), pp. 1-16

Persistent link: https://www.econbiz.de/10015195157

Construction of rating systems using global sensitivity analysis : a numerical investigation

Vallarino, Arianna; Rabitti, Giovanni; Chokami, Amir … - In: ASTIN bulletin : the journal of the International … 54 (2024) 1, pp. 25-45

Persistent link: https://www.econbiz.de/10014485608

LocalGLMnet : interpretable deep learning for tabular data

Richman, Ronald; Wüthrich, Mario V. - In: Scandinavian actuarial journal 2023 (2023) 1, pp. 71-95

Persistent link: https://www.econbiz.de/10013491052

Detection of interacting variables for generalized linear models via neural networks

Havrylenko, Yevhen; Heger, Julia - In: European Actuarial Journal 14 (2023) 2, pp. 551-580

The quality of generalized linear models (GLMs), frequently used by insurance companies, depends on the choice of interacting variables. The search for interactions is time-consuming, especially for data sets with a large number of variables, depends much on expert judgement of actuaries, and...

Persistent link: https://www.econbiz.de/10015331765

Detection of interacting variables for generalized linear models via neural networks

Havrylenko, Yevhen; Heger, Julia - In: European Actuarial Journal 14 (2023) 2, pp. 551-580

Persistent link: https://www.econbiz.de/10015406304

An interpretable machine learning workflow with an application to economic forecasting

Buckmann, Marcus; Joseph, Andreas - 2022

Persistent link: https://www.econbiz.de/10013286828

Reconciling Performance and Interpretability in Customer Churn Prediction using Ensemble Learning based on Generalized Additive Models

BOCK, K. W. DE; POEL, D. VAN DEN - Faculteit Economie en Bedrijfskunde, Universiteit Gent - 2012

requirements: strong classification performance and a high level of model interpretability. In recent literature, ensemble … Subspace Method and semiparametric GAMs as constituent classifiers, is extended to include two instruments for model … interpretability: generalized feature importance scores, and bootstrap confidence bands for smoothing splines. In an experimental …

Persistent link: https://www.econbiz.de/10011083098