PRODUCTION PLANNING AND DEAD STOCK MANAGEMENT USING SOCIAL MEDIA SCRAPPING

Abstract

The industries are currently experiencing significant growth due to hyper consumerism and mass customization, resulting in high market competition. The digital era has a high potential to scale up the market. The industry faces significant challenges in demand forecasting, production planning, and inventory management. Traditional forecasting models often fail to capture dynamic market trends, leading to overproduction, dead stock accumulation, and financial losses. This study explores the application of dynamic social media scraping as a data-driven approach to improve production planning and reduce dead stock. By leveraging social media scraping techniques to extract real-time contemporary trends from platforms such as Instagram, Pinterest, and online marketplaces, manufacturers can optimize their supply chain and align production with market demand. A sample dataset was extracted through social media scraping using a Python algorithm and processed and analysed to establish correlations between trend analysis and demand in the textile industry. Additionally, trend refresh cycles were introduced to ensure accuracy, comparing predicted demand based on social media data with actual sales performance over time. This paper presents a production and dead stock management framework integrating dynamic social media scraping with Python algorithms using machine learning and mathematical optimization models. The findings indicate that social media scraping discovers insights to significantly improve efficiency, reduce dead stock, and increase profitability in the market.