This project aims to address the supply-demand mismatch in the instant noodles market for a Fast-Moving Consumer Goods (FMCG) company. The challenge is to optimize supply quantities in warehouses to minimize inventory-related costs, enhance efficiency, and maximize profitability. The solution is data-driven, leveraging historical sales data, demand patterns, and other relevant factors.
The FMCG company, having entered the instant noodles market two years ago, faces a significant challenge with a mismatch between high demand and low supply, and vice versa, across their warehouses. This issue has resulted in inventory cost losses due to insufficient supply in high-demand regions and excess inventory in low-demand regions.
- Optimization Goal: Achieve a balance between supply and demand to minimize inventory-related costs.
- Efficiency Enhancement: Improve the overall efficiency of the supply chain management process.
- Profit Maximization: Ultimately maximize profitability by addressing supply-demand discrepancies.
The solution involves developing and implementing machine learning models to predict and optimize supply quantities in each warehouse. The models will be trained on historical sales data, demand patterns, and other relevant factors to provide data-driven insights for decision-making.
- Data Analysis: Utilize historical sales data and demand patterns for in-depth analysis.
- Predictive Modeling: Develop machine learning models to predict future demand and optimize supply.
- Efficiency Metrics: Implement metrics to measure and enhance the efficiency of the supply chain.
- Cost Optimization: Focus on minimizing inventory-related costs through strategic supply adjustments.
- Python
- Machine Learning Libraries (e.g., scikit-learn, TensorFlow)
- Data Analysis Tools (e.g., Pandas, NumPy)
- Version Control (e.g., Git)
- Documentation (e.g., Markdown)
- Python installed
- Required libraries installed (
requirements.txt
provided) - Dataset available (historical sales, demand data)