Quantile Regression
Quantile regression is a statistical method focusing on modeling the conditional quantiles of a dependent variable, providing a more comprehensive understanding of the data distribution than traditional methods that only estimate the mean. Current research emphasizes improving the accuracy and efficiency of quantile regression, particularly in high-dimensional settings and for complex data structures, through advancements in algorithms like quantile regression forests, neural networks (including those incorporating techniques like conformal prediction and evidential learning), and kernel methods. These improvements are driving applications across diverse fields, including finance (risk management), healthcare (uncertainty quantification in diagnostics), and environmental science (spatial data analysis), where robust and reliable uncertainty estimation is crucial for informed decision-making.
Papers
EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning
Parvin Malekzadeh, Zissis Poulos, Jacky Chen, Zeyu Wang, Konstantinos N. Plataniotis
Risk Analysis in Customer Relationship Management via Quantile Region Convolutional Neural Network-Long Short-Term Memory and Cross-Attention Mechanism
Yaowen Huang, Jun Der Leu, Baoli Lu, Yan Zhou