Research Director SAMBA
Kjersti Aas
- Department Statistical modelling and machine learning
- Mobile phone +47 995 69 695
- Phone number +47 22 85 26 94
- E-mail kjersti@nr.stage.dekodes.no
Projects
- Machine learning
A credit model for small and medium-sized businesses
- Statistical modelling
- Machine learning
Predicting the market value of liabilities
- Statistical modelling
DNB’s total risk assessment model
Publications
- 633 publications found
Aas, Kjersti. (2026).
Hvordan benytte AI til å forbedre kredittrisikomodeller? BI
NVA
Faglig foredrag
Aas, Kjersti. (2026).
MCCE: Monte Carlo sampling of realistic counterfactual explanations. University of Oslo
NVA
Faglig foredrag
Jullum, Martin og Aas, Kjersti. (2026).
Seminar: Datadrevet antihvitvasking og svindeldeteksjon. Norsk Regnesentral
NVA
Annen presentasjon
Aas, Kjersti. (2026).
MCCE: Monte Carlo sampling of realistic counterfactual explanations. Amsterdam University Medical Centers
NVA
Vitenskapelig foredrag
Aas, Kjersti og Rognebakke, Hanne. (2025).
Simuleringsmodell for innskuddsforpliktelser versjon IV: Brukermanual.
NVA
Rapport
Aas, Kjersti. (2025).
Model for determining the Norwegian deposit guarantee fund liabilities - Version IV: Technical report.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
Totalrisikomodell for DNB Versjon 12: Brukermanual.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
RSM Versjon 7.0.1: Økonomisk scenariogenerator.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
RSM - Versjon 7.0.1 - Teknisk rapport.
NVA
Rapport
Aas, Kjersti. (2025).
Hvordan benytte AI til å forbedre kredittrisikomodeller? BI
NVA
Faglig foredrag
Neef, Linda Reiersølmoen og Aas, Kjersti. (2025).
Modell for Solvens II - Versjon 16: Brukermanual.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2025).
Modell for Solvens II - Versjon 16: Teknisk rapport for passivamodul.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2025).
Modell for Solvens II - Versjon 16: Estimeringsmodul.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
Modell for Solvens II - Versjon 16: Teknisk rapport for ESG-modul.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
Modell for Solvens II - Versjon 16: Teknisk rapport for balansemodul.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2025).
Modell for Solvens II - Versjon 16: Modul for prising av rentegaranti.
NVA
Rapport
Neef, Linda Reiersølmoen; Aas, Kjersti og Aastveit, Marthe Elisabeth. (2025).
ALM-modell for Fremtind – Versjon 7: Brukermanual.
NVA
Rapport
Aas, Kjersti; Neef, Linda Reiersølmoen og Aastveit, Marthe Elisabeth. (2025).
ALM-modell for Fremtind – Versjon 7: Estimeringsmodulen.
NVA
Rapport
Neef, Linda Reiersølmoen; Aas, Kjersti og Aastveit, Marthe Elisabeth. (2025).
ALM-modell for Fremtind – Versjon 7: Teknisk rapport for passivamodulen.
NVA
Rapport
Aas, Kjersti; Neef, Linda Reiersølmoen og Aastveit, Marthe Elisabeth. (2025).
ALM-modell for Fremtind – Versjon 7: Teknisk rapport for balansemodulen.
NVA
Rapport
Aas, Kjersti. (2025).
Hvordan benytte AI til å forbedre kredittrisikomodeller? BI
NVA
Faglig foredrag
Aas, Kjersti. (2024).
Explainable AI: Counterfactual Explanations. Umeå University
NVA
Vitenskapelig foredrag
Aas, Kjersti. (2024).
Explainable AI: Global explanations. Umeå University
NVA
Vitenskapelig foredrag
Aas, Kjersti. (2024).
Explainable AI focusing on Shapley values and counterfactual explanations. NORA
NVA
Faglig foredrag
Redelmeier, Annabelle Alice; Jullum, Martin; Aas, Kjersti og Løland, Anders. (2024).
MCCE: Monte Carlo sampling of valid and realistic counterfactual explanations for tabular data.
Vis sammendrag
We introduce MCCE: Monte Carlo sampling of valid and realistic Counterfactual Explanations for tabular data, a novel counterfactual explanation method that generates on-manifold, actionable and valid counterfactuals by modeling the joint distribution of the mutable features given the immutable features and the decision. Unlike other on-manifold methods that tend to rely on variational autoencoders and have strict prediction model and data requirements, MCCE handles any type of prediction model and categorical features with more than two levels. MCCE first models the joint distribution of the features and the decision with an autoregressive generative model where the conditionals are estimated using decision trees. Then, it samples a large set of observations from this model, and finally, it removes the samples that do not obey certain criteria. We compare MCCE with a range of state-of-the-art on-manifold counterfactual methods using four well-known data sets and show that MCCE outperforms these methods on all common performance metrics and speed. In particular, including the decision in the modeling process improves the efficiency of the method substantially.
Olsen, Lars Henry Berge; Glad, Ingrid Kristine; Jullum, Martin og Aas, Kjersti. (2024).
A comparative study of methods for estimating model-agnostic Shapley value explanations.
Vis sammendrag
Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learning models in the industry and academia. There are several algorithmic approaches for computing different versions of Shapley value explanations. Here, we consider Shapley values incorporating feature dependencies, referred to as conditional Shapley values, for predictive models fitted to tabular data. Estimating precise conditional Shapley values is difficult as they require the estimation of non-trivial conditional expectations. In this article, we develop new methods, extend earlier proposed approaches, and systematize the new refined and existing methods into different method classes for comparison and evaluation. The method classes use either Monte Carlo integration or regression to model the conditional expectations. We conduct extensive simulation studies to evaluate how precisely the different method classes estimate the conditional expectations, and thereby the conditional Shapley values, for different setups. We also apply the methods to several real-world data experiments and provide recommendations for when to use the different method classes and approaches. Roughly speaking, we recommend using parametric methods when we can specify the data distribution almost correctly, as they generally produce the most accurate Shapley value explanations. When the distribution is unknown, both generative methods and regression models with a similar form as the underlying predictive model are good and stable options. Regression-based methods are often slow to train but quickly produce the Shapley value explanations once trained. The vice versa is true for Monte Carlo-based methods, making the different methods appropriate in different practical situations.
Aas, Kjersti. (2024).
MCCE: Monte Carlo sampling of realistic counterfactual explanations. Big Insight and Integreat
NVA
Vitenskapelig foredrag
Aas, Kjersti og Neef, Linda Reiersølmoen. (2024).
Modell for Solvens II - Versjon 15: Teknisk rapport for balansemodul.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2024).
Modell for Solvens II - Versjon 15: Teknisk rapport for ESG-modul.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2024).
RSM Versjon 6.0.1 - Økonomisk scenariogenerator.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2024).
Modell for Solvens II - Versjon 15: Modul for prising av rentegaranti.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2024).
Modell for Solvens II - Versjon 15: Estimeringsmodul.
NVA
Rapport
Aas, Kjersti. (2024).
Hvordan benytte AI til å forbedre kredittrisikomodeller? Svea Finans AS
NVA
Faglig foredrag
Neef, Linda Reiersølmoen og Aas, Kjersti. (2024).
Modell for Solvens II - Versjon 15: Brukermanual.
NVA
Rapport
Aas, Kjersti; Charpentier, Arthur; Huang, Fei og Richman, Ronald. (2024).
Insurance analytics: Prediction, explainability, and fairness.
Vis sammendrag
The expanding application of advanced analytics in insurance has generated numerous opportunities, such as more accurate predictive modeling powered by machine learning and artificial intelligence (AI) methods, the utilization of novel and unstructured datasets, and the automation of key operations. Significant advances in these areas are being made through novel applications and adaptations of predictive modeling techniques for insurance purposes, while, concurrently, rapid advances in machine learning methods are being made outside of the insurance sector. However, these innovations also bring substantial challenges, particularly around the transparency, explanation, and fairness of complex algorithmic models and the economic and societal impacts of their adoption in decision-making. As insurance is a highly regulated industry, models may be required by regulators to be explainable, in order to enable analysis of the basis for decision making. Due to the societal importance of insurance, significant attention is being paid to ensuring that insurance models do not discriminate unfairly. In this special issue, we feature papers that explore key issues in insurance analytics, focusing on prediction, explainability, and fairness.
Jullum, Martin og Aas, Kjersti. (2024).
Statistiske metoder versus maskinlæringsmetoder. Den Norske Aktuarforening
NVA
Faglig foredrag
Jullum, Martin; Aase, Frida Svendal og Aas, Kjersti. (2024).
More effective computation of Shapley values. Universitetet i Tromsø
NVA
Vitenskapelig foredrag
Aas, Kjersti. (2024).
Kredittscoring, forklarbar AI og syntetiske data. SpareBank1 gruppen
NVA
Faglig foredrag
Jullum, Martin og Aas, Kjersti. (2024).
Finetuning credit scoring ensemble models for FundingPartner.
NVA
Rapport
Jullum, Martin; Aas, Kjersti og Løland, Anders. (2024).
Introduction to the 1st Oslo Invitational Workshop on Model-Agnostic Explainable AI. Norwegian Computing Center, BigInsight, Integreat
NVA
Faglig foredrag
Jullum, Martin; Aas, Kjersti; Løland, Anders; Aase, Frida Svendal og Olsen, Lars Henry Berge. (2024).
On conditional Shapley values for prediction explanation - Adaptive & variance stabilizing estimation with KernelSHAP. University of Bremen
NVA
poster
Jullum, Martin; Aas, Kjersti; Aase, Frida Svendal og Løland, Anders. (2024).
Recent computational advances in Shapley values based prediction explanation. Norwegian Statistical Association
NVA
Vitenskapelig foredrag
Neef, Linda Reiersølmoen og Aas, Kjersti. (2024).
Modell for Solvens II - Versjon 15: Teknisk rapport for passivamodul.
NVA
Rapport
Mancisidor, Rogelio Andrade; Kampffmeyer, Michael Christian; Aas, Kjersti og Jenssen, Robert. (2023).
Discriminative multimodal learning via conditional priors in generative models.
Vis sammendrag
Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data, which depict an object from different viewpoints. These two learning mechanisms can, however, conflict with each other and representations can fail to embed information on the data modalities. This research studies the realistic scenario in which all modalities and class labels are available for model training, e.g. images or handwriting, but where some modalities and labels required for downstream tasks are missing, e.g. text or annotations. We show, in this scenario, that the variational lower bound limits mutual information between joint representations and missing modalities. We, to counteract these problems, introduce a novel conditional multi-modal discriminative model that uses an informative prior distribution and optimizes a likelihood-free objective function that maximizes mutual information between joint representations and missing modalities. Extensive experimentation demonstrates the benefits of our proposed model, empirical results show that our model achieves state-of-the-art results in representative problems such as downstream classification, acoustic inversion, and image and annotation generation.
Løland, Anders og Aas, Kjersti. (2023).
Generation of synthetic data: methods for, lessons from and challenges with tabular data. dScience, UiO
NVA
Faglig foredrag
Neef, Linda Reiersølmoen; Engebretsen, Solveig og Aas, Kjersti. (2023).
Modellering av sannsynlighet for uførhet.
NVA
Rapport
Aas, Kjersti. (2023).
Two case studies: Model for risk of rainfall-induced water damages and use of machine learning to predict customer churn. Stockholm University
NVA
Vitenskapelig foredrag
Aas, Kjersti. (2023).
Explaining individual predictions when
features are dependent: More accurate approximations to
Shapley values. NR and UiO
NVA
Faglig foredrag
Aas, Kjersti. (2023).
MCCE: Monte Carlo sampling of valid and realistic Counterfactual Explanations for tabular data. NTNU and SpareBank 1 SMN
NVA
Faglig foredrag
Aas, Kjersti og Neef, Linda Reiersølmoen. (2023).
RSM Versjon 5.0.2 Økonomisk scenariogenerator.
NVA
Rapport
Aas, Kjersti og Aastveit, Marthe Elisabeth. (2023).
Simuleringsmodell for innskuddsforpliktelser versjon III: Brukermanual.
NVA
Rapport
Aas, Kjersti og Wahl, Jens Christian. (2023).
Model for determining the Norwegian deposit guarantee fund liabilities - Version III: Technical report.
NVA
Rapport
Aas, Kjersti. (2023).
Explainable AI: LIME and Counterfactual explanations. NTNU
NVA
Faglig foredrag
Neef, Linda Reiersølmoen og Aas, Kjersti. (2023).
Modell for Solvens II - Versjon XIV: Estimeringsmodul.
NVA
Rapport
Aas, Kjersti; Neef, Linda Reiersølmoen og Aastveit, Marthe Elisabeth. (2023).
ALM-modell for Fremtind - Versjon 5: Estimeringsmodulen.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2023).
Modell for Solvens II - Versjon XIV: Teknisk rapport for passivamodul.
NVA
Rapport
Jullum, Martin; Aas, Kjersti; Løland, Anders og Redelmeier, Annabelle Alice. (2023).
A ridiculously simple approach to counterfactual explanations. NTNU Trondheim
NVA
Vitenskapelig foredrag
Jullum, Martin; Aas, Kjersti; Løland, Anders og Redelmeier, Annabelle Alice. (2023).
A ridiculously simple approach to counterfactual explanations. LMU Munich
NVA
Vitenskapelig foredrag
Aas, Kjersti og Neef, Linda Reiersølmoen. (2023).
Modell for Solvens II - Versjon XIV: Modul for prising av rentegaranti.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2023).
Modell for Solvens II - Versjon XIV: Teknisk rapport for balansemodul.
NVA
Rapport
Neef, Linda Reiersølmoen; Aas, Kjersti og Aastveit, Marthe Elisabeth. (2023).
ALM-modell for Fremtind - Versjon 5: Brukermanual.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2023).
Modell for Solvens II - Versjon XIV: Teknisk rapport for ESG-modul.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2023).
Modell for Solvens II - Versjon XIV: Brukermanual.
NVA
Rapport
Neef, Linda Reiersølmoen; Aas, Kjersti og Aastveit, Marthe Elisabeth. (2023).
ALM-modell for Fremtind - Versjon 5: Teknisk rapport for passivamodulen.
NVA
Rapport
Aas, Kjersti; Neef, Linda Reiersølmoen og Aastveit, Marthe Elisabeth. (2023).
ALM-modell for Fremtind - Versjon 5: Teknisk rapport for balansemodulen.
NVA
Rapport
Aas, Kjersti. (2023).
Bruk av AI i finans og forsikring – hva er våre erfaringer? Ung i Finans
NVA
Faglig foredrag
Wahl, Jens Christian og Aas, Kjersti. (2022).
Modeling claim frequency for car insurance using meteorological data.
NVA
Rapport
Olsen, Lars Henry Berge; Glad, Ingrid Kristine; Jullum, Martin og Aas, Kjersti. (2022).
Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features.
Vis sammendrag
Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical foundation in the field of cooperative game theory. Precise Shapley value estimates for dependent data rely on accurate modeling of the dependencies between all feature combinations. In this paper, we use a variational autoencoder with arbitrary conditioning (VAEAC) to model all feature dependencies simultaneously. We demonstrate through comprehensive simulation studies that our VAEAC approach to Shapley value estimation outperforms the state-of-the-art methods for a wide range of settings for both continuous and mixed dependent features. For high-dimensional settings, our VAEAC approach with a non-uniform masking scheme significantly outperforms competing methods. Finally, we apply our VAEAC approach to estimate Shapley value explanations for the Abalone data set from the UCI Machine Learning Repository.
Aas, Kjersti og Neef, Linda Reiersølmoen. (2022).
Modell for Solvens II - Versjon XIII: Teknisk rapport for balansemodul.
NVA
Rapport
Aas, Kjersti. (2022).
Bruk av data fra Brønnøysundregisteret og Norges domstoler i kredittscoringsmodell for FundingPartner.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2022).
Modell for Solvens II - Versjon XIII: Teknisk rapport for passivamodul.
NVA
Rapport
Günther, Clara-Cecilie og Aas, Kjersti. (2022).
Use of news sentiments in credit scoring model for FundingPartner.
NVA
Rapport
Aas, Kjersti og Neef, Linda Reiersølmoen. (2022).
Modell for Solvens II - Versjon XIII: Modul for prising av rentegaranti.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2022).
Modell for Solvens II - Versjon XIII: Estimeringsmodul.
NVA
Rapport
Neef, Linda Reiersølmoen og Aas, Kjersti. (2022).
Modell for Solvens II - Versjon XIII: Brukermanual.
NVA
Rapport
Aas, Kjersti og Günther, Clara-Cecilie. (2022).
Counterfactual explanations for FundingPartner’s credit
scoring model.
NVA
Rapport
Mancisidor, Rogelio Andrade; Kampffmeyer, Michael; Aas, Kjersti og Jenssen, Robert. (2022).
Generating customer's credit behavior with deep generative models.
Vis sammendrag
Innovation is considered essential for today's organizations to survive and thrive. Researchers have also stressed the importance of leadership as a driver of followers' innovative work behavior (FIB). Yet, despite a large amount of research, three areas remain understudied: (a) The relative importance of different forms of leadership for FIB; (b) the mechanisms through which leadership impacts FIB; and (c) the degree to which relationships between leadership and FIB are generalizable across cultures. To address these lacunae, we propose an integrated model connecting four types of positive leadership behaviors, two types of identification (as mediating variables), and FIB. We tested our model in a global data set comprising responses of N = 7,225 participants from 23 countries, grouped into nine cultural clusters. Our results indicate that perceived LMX quality was the strongest relative predictor of FIB. Furthermore, the relationships between both perceived LMX quality and identity leadership with FIB were mediated by social identification. The indirect effect of LMX on FIB via social identification was stable across clusters, whereas the indirect effects of the other forms of leadership on FIB via social identification were stronger in countries high versus low on collectivism. Power distance did not influence the relations.
Aas, Kjersti. (2022).
Bruk av AI i finans og forsikring - hva er våre erfaringer? Finans Norge
NVA
Faglig foredrag
Aastveit, Marthe Elisabeth; Rognebakke, Hanne Therese Wist og Aas, Kjersti. (2022).
Evaluering av XGBoost-modellen for prisestimater.
NVA
Rapport
Aas, Kjersti. (2021).
Explainable AI: Counterfactual explanations and Shapley values. NTNU
NVA
Faglig foredrag