Less Discriminatory Alternative and Interpretable XGBoost Framework for Binary Classification

Fair lending practices and model interpretability are crucial concerns in the financial industry, especially given the increasing use of complex machine learning models. In response to the Consumer Financial Protection Bureau's (CFPB) requirement to protect consumers against unlawful discrimination, we introduce LDA-XGB1, a novel less discriminatory alternative (LDA) machine learning model for fair and interpretable binary classification. LDA-XGB1 is developed through biobjective optimization that balances accuracy and fairness, with both objectives formulated using binning and information value. It leverages the predictive power and computational efficiency of XGBoost while ensuring inherent model interpretability, including the enforcement of monotonic constraints. We evaluate LDA-XGB1 on two datasets: SimuCredit, a simulated credit approval dataset, and COMPAS, a real-world recidivism prediction dataset. Our results demonstrate that LDA-XGB1 achieves an effective balance between predictive accuracy, fairness, and interpretability, often outperforming traditional fair lending models. This approach equips financial institutions with a powerful tool to meet regulatory requirements for fair lending while maintaining the advantages of advanced machine learning techniques.

Development of a Connected and Automated Vehicle Longitudinal Control Model

It is envisioned that, in the future, most vehicles on our roadway will be controlled autonomously and will be connected via vehicle to everything (V2X) wireless communication networks. Developing a connected and automated vehicle (CAV) longitudinal controller, which will consider safety, comfort and operational efficiency simultaneously, is a challenge. A CAV longitudinal controller is a complex system where a vehicle senses immediate upstream vehicles using its sensors and receives information about its surroundings via wireless connectivity, and move forward accordingly. In this study, we develop an information-aware driver model (IADM) that utilizes information regarding an immediate upstream vehicle of a subject CAV through CAV sensors and V2X connectivity while considering passenger comfort and operational efficiency along with maintaining safety gap for longitudinal vehicle motion of the autonomous vehicle. Unlike existing driver models for longitudinal control, the IADM intelligently fuses data received from in vehicle sensors, and immediate upstream vehicles of the subject CAV through wireless connectivity, and IADM parameters do not need to be calibrated for different traffic states, such as congested and non congested traffic conditions. It only requires defining the subject CAVs maximum acceleration and deceleration limit, and computation time that is needed to update the subject CAVs trajectory from its previous state. Our analyses suggest that the IADM (i) is able to maintain safety using a newly defined safe gap function depending on the speed and reaction time of a CAV; (ii) shows local stability and string stability and (iii) provides riding comfort for a range of autonomous driving aggressiveness depending on the passenger preferences.