A RULE-BASED ANALYTICS FRAMEWORK FOR DELIVERY DELAY ANALYSIS AND SLA OPTIMIZATION IN QUICK COMMERCE

Quick commerce platforms operate under strict service level agreements (SLAs), where even small deliverydelays can significantly impact customer satisfaction. Managing such delays is challenging due to high ordervolumes, limited delivery personnel, demand fluctuations, and operational bottlenecks across different zones. Thispaper presents a rule-based analytics framework for analysing delivery performance and optimizing SLAcompliance in quick commerce operations. The proposed system uses historical delivery data stored in a relationaldatabase and applies descriptive and diagnostic analytics to identify delay patterns and root causes. The frameworkincludes multiple analytical modules such as overview analysis, delay root cause identification, micro-zoneperformance evaluation, rider efficiency analysis, warehouse picking analysis, and a risk-based simulationmodule. A workload-based what-if simulation approach is employed to evaluate the impact of operational changessuch as rider addition and order load reduction on SLA performance. The system is implemented using Pythonfor analytics, MySQL for data storage, and Streamlit for interactive visualization. Experimental results from areal-world city-level dataset demonstrate that the proposed framework effectively identifies operationalbottlenecks and provides actionable insights for improving delivery efficiency and SLA compliance.