Enhancing Supply Chain Efficiency with IoT and Data Analytics

This study aims at exploring the use of internet of things technology and data analytics in the field of supply chain management. Using a range of software tools, including Apache Kafka, Apache NiFi, Python libraries such as Pandas, and Scikit-learn, the study accumulated, assimilated, and quantified data from IoT sensors, supply chain systems, and qualitative interviews. The primary data sources are primary supply chain data history and IoT sensor data while secondary data includes academic and industrial journals, and reports. This paper presents a number of basic quantitative measures showing the general performance indicators: the average percentage of order fulfilment as $\mathbf{9 2. 5 \%}$ and the inventory turnover ratio equalling 6.2. When using linear regression, random forest, and LSTM neural network, the models reveal the mean absolute errors of demand forecasting between 80 and $\mathbf{1 2 0}$ units. The results suggest that IoT and data analysis offer significant opportunities to create value through the integration of SC, cost cutting, and higher customer satisfaction. It has now become essential for organizations to effectively apply data trends to enable competitive gains within the complex business setting to foster operational efficacy and stability.