SmallML: Bayesian Transfer Learning for Small-Data Predictive Analytics

TL;DR

SmallML is a Bayesian transfer learning framework that enables accurate predictive analytics on small datasets typical of SMEs, combining transfer learning, hierarchical Bayesian modeling, and conformal prediction for uncertainty quantification.

Contribution

The paper introduces SmallML, a novel three-layer Bayesian transfer learning architecture specifically designed for small-data SME applications, achieving high accuracy and reliable uncertainty estimates.

Findings

Achieves 96.7% AUC with 100 observations per business.

Improves prediction accuracy by +24.2 points over independent logistic regression.

Provides finite-sample coverage guarantees with conformal prediction.

Abstract

Small and medium-sized enterprises (SMEs) represent 99.9% of U.S. businesses yet remain systematically excluded from AI due to a mismatch between their operational scale and modern machine learning's data requirements. This paper introduces SmallML, a Bayesian transfer learning framework achieving enterprise-level prediction accuracy with datasets as small as 50-200 observations. We develop a three-layer architecture integrating transfer learning, hierarchical Bayesian modeling, and conformal prediction. Layer 1 extracts informative priors from 22,673 public records using a SHAP-based procedure transferring knowledge from gradient boosting to logistic regression. Layer 2 implements hierarchical pooling across J=5-50 SMEs with adaptive shrinkage, balancing population patterns with entity-specific characteristics. Layer 3 provides conformal sets with finite-sample coverage guarantees P(y in C(x)) >= 1-alpha for distribution-free uncertainty quantification. Validation on customer churn data demonstrates 96.7% +/- 4.2% AUC with 100 observations per business -- a +24.2 point improvement over independent logistic regression (72.5% +/- 8.1%), with p < 0.000001. Conformal prediction achieves 92% empirical coverage at 90% target. Training completes in 33 minutes on standard CPU hardware. By enabling enterprise-grade predictions for 33 million U.S. SMEs previously excluded from machine learning, SmallML addresses a critical gap in AI democratization. Keywords: Bayesian transfer learning, hierarchical models, conformal prediction, small-data analytics, SME machine learning