Intelligent Warehouse Allocator for Optimal Regional Utilization
This work addresses inventory management challenges for online fashion retailers like Myntra, though it is incremental as it applies existing methods to a specific domain.
The paper tackles the problem of optimizing warehouse allocations for fashion inventory to minimize logistics costs and delivery times by using machine learning to estimate regional demand and integer programming to allocate inventory under capacity constraints, resulting in significant improvements in Regional Utilization and Percentage Two-day-delivery metrics.
In this paper, we describe a novel solution to compute optimal warehouse allocations for fashion inventory. Procured inventory must be optimally allocated to warehouses in proportion to the regional demand around the warehouse. This will ensure that demand is fulfilled by the nearest warehouse thereby minimizing the delivery logistics cost and delivery times. These are key metrics to drive profitability and customer experience respectively. Warehouses have capacity constraints and allocations must minimize inter warehouse redistribution cost of the inventory. This leads to maximum Regional Utilization (RU). We use machine learning and optimization methods to build an efficient solution to this warehouse allocation problem. We use machine learning models to estimate the geographical split of the demand for every product. We use Integer Programming methods to compute the optimal feasible warehouse allocations considering the capacity constraints. We conduct a back-testing by using this solution and validate the efficiency of this model by demonstrating a significant uptick in two key metrics Regional Utilization (RU) and Percentage Two-day-delivery (2DD). We use this process to intelligently create purchase orders with warehouse assignments for Myntra, a leading online fashion retailer.