Optimizing Inventory Management in Supply Chains Through Predictive Analytics and Big Data Techniques

Abstract

The research will result in meaningful recommendations that could be picked by organizations to implement predictive analytics and big data to optimize inventory levels, streamline the supply chain processes, and increase the overall supply chain resilience. This paper was quantitative, whereby structured survey was conducted to provide information to supply chain managers, data scientists and IT specialists. Initially, 250 samples were collected; 30 were discarded due to incomplete responses, leaving 220 valid responses for analysis. The data was analyzed using descriptive statistics, regression analysis, factor analysis and ARIMA forecasting. The ANOVA test demonstrated that predictive analytics as a decision-making tool can greatly enhance demand forecasting and reduce stockouts and overstocking, with an F-statistic of 15.2 and a p-value of 0.0001, indicating that Hypothesis 1 is accepted.  The regression model demonstrated that operational efficiency is positively affected by real-time insight (β₁ = 0.35) and cost reduction (β₂ = 0.42) enabled by big data, with R² and F value of 0.62 and 180.00, respectively, supporting Hypothesis 2. Such results highlight that big data techniques can improve decision-making and performance by providing practical insights and enhancing cost-effectiveness. Data quality, integration issues, and technological capabilities were also identified as the most significant challenges to applying big data and predictive analytics in factor analysis, with data quality (loading = 0.92) as the most significant challenge, supporting hypothesis 3. Finally, the ARIMA prediction showed better inventory optimization (4.20), supply chain efficiency (4.50), and resilience (4.10), which were in favor of Hypothesis 4. These projections suggest that supply chains are becoming more resilient through the application of predictive analytics and big data, resulting in reduced lead times, greater supplier collaboration, and higher customer satisfaction