Prediction Model

Prediction models aim to accurately forecast outcomes based on input data, with current research focusing on improving model robustness, interpretability, and fairness. Commonly employed architectures include linear regression, decision trees, support vector machines, neural networks (including deep learning models and transformers), and ensemble methods like XGBoost, often enhanced by techniques like data preprocessing, feature engineering, and counterfactual explanations. These advancements are crucial for diverse applications, ranging from healthcare and finance to environmental monitoring and autonomous systems, improving decision-making and resource allocation across various sectors.

Papers

February 16, 2022

The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining
Murat Kuzlu, Ferhat Ozgur Catak, Umit Cali, Evren Catak, Ozgur Guler
Deep Neural Network Adversarial Attack Adversarial Example mmWave Signal Prediction Model Beam Prediction Adversarial Retraining Defensive Distillation

December 2, 2021

Who will dropout from university? Academic risk prediction based on interpretable machine learning
Shudong Yang
Predictive Model Interpretable Machine Learning Prediction Model Academic Integrity

Prediction Model

Papers

The Adversarial Security Mitigations of mmWave Beamforming Prediction Models using Defensive Distillation and Adversarial Retraining

Who will dropout from university? Academic risk prediction based on interpretable machine learning