Risk Prediction
Risk prediction research aims to develop accurate and reliable models for forecasting future events, spanning diverse domains like finance, healthcare, and transportation. Current efforts focus on leveraging advanced machine learning techniques, including deep learning architectures such as graph neural networks, recurrent neural networks (like LSTMs), and ensemble methods (e.g., combining XGBoost, LightGBM, and TabNet), often enhanced by techniques to address data imbalance and missing values. These advancements hold significant potential for improving decision-making in various sectors by enabling more precise risk assessments and proactive interventions, ultimately leading to better resource allocation and improved outcomes. Furthermore, research emphasizes explainability and fairness in risk prediction models, addressing concerns about bias and transparency.
Papers
Credit card score prediction using machine learning models: A new dataset
Anas Arram, Masri Ayob, Musatafa Abbas Abbood Albadr, Alaa Sulaiman, Dheeb Albashish
MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation
Yuan Zhong, Suhan Cui, Jiaqi Wang, Xiaochen Wang, Ziyi Yin, Yaqing Wang, Houping Xiao, Mengdi Huai, Ting Wang, Fenglong Ma