Optimizing Supply Chain Logistics with IOT And Machine Learning: From Data Collection to Decision Making Based on Refined Battle Royale Optimizer Weighted Random Forest

In today's interconnected and competitive global market, the efficiency of supply chain (SC) logistics plays a critical role in the success of businesses. As SCs become more complex and dynamic, traditional methods of managing logistics and inventory have struggled with the demand for real-time decision-making. The study's goal is to establish SC logistics using the Internet of Things (IoT) and machine learning (ML) to make decisions. This study proposed a novel Refined Battle Royale optimizer Weighted Random Forest (RBR-WRF) model is to improve SC performance through demand volume prediction. Real-time data collected through IoT sensors, the framework optimizes key logistics processes such as demand forecasting, inventory management, and transportation planning. The data was gathered from the Kaggle source. Data preparation includes data cleaning, outliers’ detection to handling missing values and transforming raw data to improve analysis with min-max normalization with z-score. This framework is a predictive model based on the WRF, optimized through RBRO. The model accurately predicts demand volume by optimizing hyperparameters. Tuning the WRF model and adjusting the weight values of learning components. The suggested approach is implemented with Python software. The performance of the suggested method is evaluated in terms of MSE (0.00324), MAE (0.04315), RMSE (0.05412), and MAPE (3.41%) and the t-value statistical test is 3.37. The findings revealed that the suggested predictive model achieves an average inaccuracy in demand volume forecast, displaying a minimal reduction compared to traditional approaches. Also, this model's enhancement of SC logistics performance reduces delays and better efficiency in the company. This combination of IoT and ML in SC logistics provides businesses with a reliable solution for data-driven decision-making, allowing them to respond to changing market conditions while increasing operational efficiency.