Their novel solutions outperformed GPT -4, showcasing FinBen's potential to drive innovations in financial LLMs.

In the United States, health insurance is a critical component of individuals' ability to access health care.

Despite these successes, the highly technical nature of financial texts requires domain-specific LLMs to understand complex financial language and concepts effectively.

We examine whether these static fairness constraints mitigate or worsen the qualification disparity in the long-run. Our work can be applied to a variety of applications such as recruitment and bank lending. In these applications, aninstitute observesindividuals' features (e.g., credit scores), and makes myopic decisions(e.g., issue loans) by assessing such features against some variables of interest (e.g., ability torepay) which are unknown and unobservable tothe institute when making decisions.

However, NAMs (likeallGAMs), are not causal models.

Survival analysis has become a standard approach for modelling time to default by time-varying covariates in credit risk. Unlike most existing methods that implicitly assume a stationary data-generating process, in practise, mortgage portfolios are exposed to various forms of data drift caused by changing borrower behaviour, macroeconomic conditions, policy regimes and so on. This study investigates the impact of data drift on survival-based credit risk models and proposes a dynamic joint modelling framework to improve robustness under non-stationary environments. The proposed model integrates a longitudinal behavioural marker derived from balance dynamics with a discrete-time hazard formulation, combined with landmark one-hot encoding and isotonic calibration. Three types of data drift (sudden, incremental and recurring) are simulated and analysed on mortgage loan datasets from Freddie Mac. Experiments and corresponding evidence show that the proposed landmark-based joint model consistently outperforms classical survival models, tree-based drift-adaptive learners and gradient boosting methods in terms of discrimination and calibration across all drift scenarios, which confirms the superiority of our model design.

AB S TRACT This study evaluates the performance of various classifiers in three distinct models: r esponse, r isk, and r esponse - r isk, concerning credit card mail campaigns and default prediction. In the r esponse model, the Extra Trees classifier demonstrates the highest recall level (79.1%), emphasizing its effectiveness in identifying potential responders to targeted credit card offers. Conversely, in the r isk model, the Random Forest classifier exhibits remarkable specificity of 84.1%, crucial for identifying customers least likely to default. Furthermore, in the multi - class r esponse - r isk model, the Random Forest classifier achieve s the highest accuracy (83.2%), indicating its efficacy in discerning both potential responders to credit card mail campaign and low - risk credit card users . In this study, we optimized various performance metrics to solve a specific credit risk and mail responsiveness business problem.