Data analysis and predictive modeling project for an FMCG company to optimize shipment weights across warehouses using Python (EDA + ML), Tableau (dashboards), and KNIME (workflow automation)
This project focuses on optimizing supply and distribution for an FMCG (Fast-Moving Consumer Goods) company that recently entered the instant noodles business. The company faced demand–supply mismatches — overstocking in low-demand areas and shortages in high-demand ones.
The goal is to use historical data and machine learning to:
Predict optimum shipment weight (tons) for each warehouse.
Identify regional demand patterns.
Create interactive dashboards for management and stakeholders.