LINEAR REGRESSION-BASED PREDICTIVE BIG DATA ANALYTICS FOR SUPPLY CHAIN DEMAND PLANNING

Abstract

With the increasing amount of data generated by various sources, traditional demand planning faces challenges in terms of accuracy and efficiency. Big data analytics, on the other hand, provides the means to process vast amounts of data in real-time and uncover hidden patterns and relationships. The integration of big data analytics can significantly improve the accuracy and timeliness of demand planning, leading to better decision-making and ultimately, improved supply chain analytics performance. This research proposes an approach for supply chain demand planning using Linear Regression-based predictive big data analytics. The integration of predictive analytics has the potential to overcome the limitations of supply chain analytics. The research methodology will use a Linear Regression-based predictive analysis model for historical quantitative analysis of demand planning, which is tested using real-world data from a supply chain company. The dataset that will be used is from the dev environment of the company that we are working for. The dataset consists of over 21,000 customer orders that were made from 2016, with the customer data, address, invoices and order items. The results of this research will show that the proposed predictive analysis model outperforms traditional models in terms of accuracy of predicting future customer order demands. The findings of this research have the potential to improve the demand planning  in supply chain management and help organizations make more informed decisions