5 papers
Noise-adjusted turnover in estimated networks
Sultan Amed, Sayantan Banerjee
Economic networks are often estimated separately over two periods, and changes in their edge sets are interpreted as structural rewiring. Since both networks are estimated, observe…
BayPrAnoMeta: Bayesian Proto-MAML for Few-Shot Industrial Image Anomaly Detection
Soham Sarkar, Tanmay Sen, Sayantan Banerjee
Industrial image anomaly detection is a challenging problem owing to extreme class imbalance and the scarcity of labeled defective samples, particularly in few-shot settings. We pr…
FSL-BDP: Federated Survival Learning with Bayesian Differential Privacy for Credit Risk Modeling
Sultan Amed, Tanmay Sen, Sayantan Banerjee
Credit risk models are a critical decision-support tool for financial institutions, yet tightening data-protection rules (e.g., GDPR, CCPA) increasingly prohibit cross-border shari…
DP-FedSOFIM: Differentially Private Federated Stochastic Optimization using Regularized Fisher Information Matrix
Sidhant Nair, Tanmay Sen, Mrinmay Sen +1
Differentially private federated learning (DP-FL) often suffers from slow convergence under tight privacy budgets because the noise required for privacy preservation degrades gradi…
PDx -- Adaptive Credit Risk Forecasting Model in Digital Lending using Machine Learning Operations
Sultan Amed, Chan Yu Hang, Sayantan Banerjee
This paper presents PDx, an adaptive, machine learning operations (MLOps) driven decision system for forecasting credit risk using probability of default (PD) modeling in digital l…