Abstract
Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-characterized. Existing benchmarks rarely address the hundreds of millions of rows and high-cardinality features typical of industrial-operational datasets. We evaluate five multi-column two-sample tests (marginal, projection-based, and kernel embedding methods) across three complementary environments: the Harvard Dataverse, a validated Failing Loudly reproduction (mean absolute error between 0.030 and 0.053), and a novel synthetic-injection benchmark on the 137.5-million-row Trendyol collection-ranking feature table. Testing four drift types across two severity-scope regimes, we demonstrate that distributed Maximum Mean Discrepancy with Random Fourier Features on Apache Spark scales robustly. Averaged over the four drift types in the strong regime and under a calibrated threshold, it achieves a Pearson correlation of r = 0.940 with expected drift magnitude, an 80.4% true positive rate, and a 3.2% false positive rate. Conversely, the per-dimension Kolmogorov-Smirnov test failed due to statistic saturation from ID-like columns under asymmetric sampling, establishing a critical constraint for large-scale sampling design. At weak configurations (realized-flip fractions of at most 0.57%), detectors struggled to reliably discriminate, highlighting the need for future intensity-grid power analyses to distinguish fundamental sensitivity bounds from scalable threshold shifts.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pullu, C., Arslan, M. E., Balkac, B., Balta, A. O., Palaci, C. C., Yilmaz, F. C., & Cakir, A. (2026). Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations. https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations
MLA 9
Pullu, Cagdas, et al. "Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations." https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations.
Chicago (author–date)
Pullu, Cagdas, Mahmut Emir Arslan, Bugra Balkac, Aylin Ondersev Balta, Cihangir Celal Palaci, Fikri Cem Yilmaz, and Altan Cakir. 2026. "Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations." https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations.
Harvard
Pullu, C., Arslan, M. E., Balkac, B., Balta, A. O., Palaci, C. C., Yilmaz, F. C. and Cakir, A. (2026) 'Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations', Available at: https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations.
Vancouver
Pullu C, Arslan ME, Balkac B, Balta AO, Palaci CC, Yilmaz FC, et al. Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations. https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations
IEEE
C. Pullu, M. E. Arslan, B. Balkac, A. O. Balta, C. C. Palaci, F. C. Yilmaz, and A. Cakir, "Beyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce Operations," https://omanscience.com/en/articles/beyond-marginal-monitoring-distributed-joint-distribution-testing-for-data-concept-drift-in-large-scale-e-commerce-operations.