Data-Driven Fulfillment Optimization for Time-Sensitive Teamwear and Sporting Goods Distribution

Abstract

This study examined the relationships among data-driven operational capabilities, fulfillment efficiency, delivery reliability, and cost–service performance in time-sensitive teamwear and sporting-goods distribution. The research adopted a quantitative analytical framework incorporating demand forecasting, inventory availability, warehouse productivity, customization processing, capacity utilization, and transportation reliability. An dataset comprising 2,400 customer orders was used to demonstrate descriptive statistics, correlation analysis, multiple regression, logistic regression, subgroup comparisons, effect-size estimation, and predictive validation. Institutional customers represented 60.0% of transactions, while customized merchandise accounted for 65.0%. Inventory record accuracy averaged 96.8%, stock availability reached 94.5%, and warehouse picking accuracy averaged 97.2%. The on-time delivery and perfect-order rates were 88.0% and 85.0%, respectively. Correlation analysis indicated negative associations between inventory availability and fulfillment lead time (r = −0.51) and positive associations between transportation lead time and fulfillment duration (r = 0.67). Customized orders required an average of 5.20 days and USD 32.60 per transaction, compared with 3.49 days and USD 20.60 for standardized merchandise. The integrated fulfillment model demonstrated an explanatory performance of R² = 0.72, compared with 0.46 for the operational-function model. Predictive evaluation indicated reductions in forecasting mean absolute error from 8.42 to 5.16 units and improvements in delivery classification ROC-AUC from 0.760 to 0.880. Under the hypothetical integrated operating scenario, fulfillment expenditure decreased from USD 28.40 to USD 25.90 per order, on-time delivery increased from 88.0% to 92.5%, and average fulfillment lead time declined from 4.60 to 3.95 days. These patterns suggested potential advantages of coordinated forecasting, inventory control, customization scheduling, and transportation management. However, the numerical estimates were hypothetical rather than empirically verified. The study therefore contributed an integrated quantitative framework for evaluating operational relationships, predictive performance, and cost–service optimization, while emphasizing the necessity of validated transaction-level data for establishing reliable empirical conclusions.