Predictive Inventory Optimization for Reducing Stockouts and Excess Inventory in U.S. Sports and Apparel Operations

Authors

  • Md Maksudul Hasan Managing Director, Good Buy Incorporated Author
  • Md Takbir Hossen Sarker Washington university of Science and Technology, Alexandria, Virginia, USA Author

DOI:

https://doi.org/10.63125/8djn1j48

Keywords:

Predictive Inventory Optimization, Stockout Reduction, Excess Inventory Reduction, Predictive Analytics, Sports and Apparel Operations

Abstract

This study addresses the persistent inventory imbalance problem in U.S. sports and apparel operations, where seasonal demand, short product life cycles, large SKU assortments, omnichannel selling, inaccurate inventory records, and delayed replenishment can produce stockouts and excess inventory simultaneously. The purpose was to quantitatively examine how predictive inventory optimization capabilities influence stockout reduction, excess inventory reduction, and overall inventory optimization performance across multiple enterprise cases. A quantitative, explanatory, cross-sectional, embedded multiple-case design was employed across apparel and fashion operations, sportswear and activewear businesses, omnichannel retail and distribution organizations, sporting-goods operations, and teamwear or licensed sports-merchandise cases. Purposive sampling produced 250 valid responses from inventory, supply-chain, demand-planning, forecasting, replenishment, procurement, merchandising, warehouse, distribution, and retail-operations professionals, representing an effective response rate of 87.7%. The key independent variables were demand forecasting accuracy, inventory visibility and data integration, dynamic safety-stock optimization, replenishment responsiveness, and predictive analytics capability, while stockout reduction, excess inventory reduction, and overall inventory optimization performance served as dependent outcomes. Data were collected through a structured five-point Likert questionnaire and analyzed using descriptive statistics, Cronbach’s alpha, KMO and Bartlett’s tests, Pearson correlation, and multiple linear regression in SPSS. Respondents reported strong demand forecasting accuracy (M = 4.08, SD = 0.61), predictive analytics capability (M = 4.02, SD = 0.64), stockout reduction (M = 3.94, SD = 0.67), and overall inventory optimization performance (M = 3.98, SD = 0.63). Dynamic safety-stock optimization was the strongest predictor of stockout reduction (β = .29, p < .001) and excess inventory reduction (β = .31, p < .001). The stockout model explained 64.1% of variance, the excess-inventory model 59.8%, and the overall optimization model 67.6%, with predictive analytics capability emerging as the strongest overall predictor (β = .28, p < .001). These findings imply that coordinated forecasting, inventory visibility, adaptive safety-stock control, responsive replenishment, and predictive analytics can materially strengthen inventory balance, product availability, and operational efficiency in complex sports and apparel enterprises.

Author Biography

  • Md Maksudul Hasan, Managing Director, Good Buy Incorporated

    Bachelor of Business Administration (BBA); University of Information Technology & Sciences, Bangladesh; Chattogram, Bangladesh;

Downloads

Published

2023-12-03

How to Cite

Md Maksudul Hasan, & Md Takbir Hossen Sarker. (2023). Predictive Inventory Optimization for Reducing Stockouts and Excess Inventory in U.S. Sports and Apparel Operations. Review of Applied Science and Technology , 13(12), 104–141. https://doi.org/10.63125/8djn1j48

Cited By: