A Cloud-Native Big Data Analytics and Automated Cybersecurity Risk Management Framework for Enterprise Business Intelligence: Optimizing Supply Chain Resilience and Capital Allocation in Global Retail Infrastructures

Modern global retail infrastructures, enterprise supply chains, and multitier logistics networks generate unprecedented volumes of nonstationary, heterogeneous operational data. This study addresses these operational deficiencies by introducing an expanded Cloud-Native Big Data Analytics and Automated Cybersecurity Risk Management Framework. The system integrates localized operational telemetry such as real-time inventory tracking, IoT sensor data streams, cloud security metrics, and supply chain logistics directly into an executive-level Enterprise Risk Optimization Engine. At the data ingestion layer, the framework employs an advanced K-Nearest Neighbors (K-NN) imputation protocol combined with Gaussian Noise Augmentation (GNA) to address missing telemetry and signal noise, restoring data integrity across high-speed enterprise message brokers. At the analytical modeling layer, a non-linear ensemble architecture models operational decay kinetics, inventory holding cost variations, and cyber-threat vectors. At the governance layer, game-theoretic SHAP (SHapley Additive exPlanations) attribution algorithms remove 'black-box' barriers, translating non-linear machine learning outputs into auditable corporate policy metrics. Evaluated over an extensive 18-month empirical deployment processing 12,500 telemetry records, the proposed architecture achieves an operational query latency of 12.4 ms, maintains an 89.5% classification recall under severe noise conditions (σ = 0.25), compresses unscheduled supply chain outages by 62.4%, and establishes an institutional capital recovery break-even point at 3.1 years. This expanded study incorporates 30 comprehensive numerical visual figures mapping structural, computational, security, and economic dynamics.