An optimal control model for adaptive auto-insurance pricing learns claim risks from telematics, captures multi-period driver responses to discounts, and applies Lagrangian relaxation to achieve asymptotically optimal portfolio-wide discount allocation.
Smote: synthetic minority over-sampling technique,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Q-SYNTH is a hybrid framework using a parameterized quantum circuit as the generator in a GAN to create synthetic minority-class fraud samples for tabular data, which shows reduced distribution mismatch compared to classical GANs and competitive performance in downstream detection tasks.
citing papers explorer
-
Prescriptive Optimization for Adaptive Auto-insurance Pricing with Telematics Data
An optimal control model for adaptive auto-insurance pricing learns claim risks from telematics, captures multi-period driver responses to discounts, and applies Lagrangian relaxation to achieve asymptotically optimal portfolio-wide discount allocation.
-
Q-SYNTH: Hybrid Quantum-Classical Adversarial Augmentation for Imbalanced Fraud Detection
Q-SYNTH is a hybrid framework using a parameterized quantum circuit as the generator in a GAN to create synthetic minority-class fraud samples for tabular data, which shows reduced distribution mismatch compared to classical GANs and competitive performance in downstream detection tasks.