Intelligent Warehouse Allocator for Optimal Regional Utilization

• URL: http://arxiv.org/abs/2007.05081v1
• Date: Thu, 9 Jul 2020 21:46:15 GMT
• Title: Intelligent Warehouse Allocator for Optimal Regional Utilization
• Authors: Girish Sathyanarayana and Arun Patro
• Abstract summary: We use machine learning and optimization methods to build an efficient solution to this warehouse allocation problem. 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)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• A Novel Framework for Automated Warehouse Layout Generation [5.076606750431126]
  We present an AI-driven framework for automated warehouse layout generation. The framework employs constrained beam search to derive optimal layouts within given spatial parameters. We demonstrate our method's ability to produce feasible, optimal layouts for a variety of warehouse dimensions and shapes.
  arXiv  Detail & Related papers  (2024-07-11T16:15:09Z)
• Estimating Barycenters of Distributions with Neural Optimal Transport [93.28746685008093]
  We propose a new scalable approach for solving the Wasserstein barycenter problem. Our methodology is based on the recent Neural OT solver. We also establish theoretical error bounds for our proposed approach.
  arXiv  Detail & Related papers  (2024-02-06T09:17:07Z)
• Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce [11.421159751635667]
  paper presents an integrated algorithmic framework for minimising product delivery costs in e-commerce. One of the major challenges in e-commerce is the large volume of-temporally diverse orders from multiple customers. We propose an approach that combines graph neural networks and reinforcement learning to train the node selection and vehicle agents.
  arXiv  Detail & Related papers  (2023-11-20T10:32:28Z)
• Using General Value Functions to Learn Domain-Backed Inventory Management Policies [2.0257616108612373]
  In existing literature, General Value Functions (GVFs) have primarily been used for auxiliary task learning. We use this capability to train GVFs on domain-critical characteristics such as prediction of stock-out probability and wastage quantity. We show that the GVF predictions can be used to provide additional domain-backed insights into the decisions proposed by the RL agent.
  arXiv  Detail & Related papers  (2023-11-03T08:35:54Z)
• Multi-Robot Coordination and Layout Design for Automated Warehousing [55.150593161240444]
  We show that, even with state-of-the-art MAPF algorithms, commonly used human-designed layouts can lead to congestion for warehouses with large numbers of robots. We extend existing automatic scenario generation methods to optimize warehouse layouts. Results show that our optimized warehouse layouts (1) reduce traffic congestion and thus improve throughput, (2) improve the scalability of the automated warehouses by doubling the number of robots in some cases, and (3) are capable of generating layouts with user-specified diversity measures.
  arXiv  Detail & Related papers  (2023-05-10T20:00:06Z)
• Cooperative Multi-Agent Reinforcement Learning for Inventory Management [0.5276232626689566]
  Reinforcement Learning (RL) for inventory management is a nascent field of research. We present a system with a custom GPU-parallelized environment that consists of one warehouse and multiple stores. We achieve a system that outperforms standard inventory control policies.
  arXiv  Detail & Related papers  (2023-04-18T06:55:59Z)
• Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers [51.71901155656791]
  We envision a warehouse in which dozens of mobile robots and human pickers work together to collect and deliver items within the warehouse. We develop hierarchical MARL algorithms in which a manager assigns goals to worker agents, and the policies of the manager and workers are co-trained toward maximising a global objective. Our hierarchical algorithms achieve significant gains in sample efficiency and overall pick rates over baseline MARL algorithms in diverse warehouse configurations.
  arXiv  Detail & Related papers  (2022-12-22T06:18:41Z)
• Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management [62.23979094308932]
  In our setting, the constraint on the shared resources (such as the inventory capacity) couples the otherwise independent control for each SKU. We formulate the problem with this structure as Shared-Resource Game (SRSG)and propose an efficient algorithm called Context-aware Decentralized PPO (CD-PPO) Through extensive experiments, we demonstrate that CD-PPO can accelerate the learning procedure compared with standard MARL algorithms.
  arXiv  Detail & Related papers  (2022-12-15T09:35:54Z)
• A Simulation Environment and Reinforcement Learning Method for Waste Reduction [50.545552995521774]
  We study the problem of restocking a grocery store's inventory with perishable items over time, from a distributional point of view. The objective is to maximize sales while minimizing waste, with uncertainty about the actual consumption by costumers. We frame inventory restocking as a new reinforcement learning task that exhibits behavior conditioned on the agent's actions.
  arXiv  Detail & Related papers  (2022-05-30T22:48:57Z)
• Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality [141.89413461337324]
  Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL) We propose a theoretical formulation for deployment-efficient RL (DE-RL) from an "optimization with constraints" perspective.
  arXiv  Detail & Related papers  (2022-02-14T01:31:46Z)
• Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains [17.260459603456745]
  This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. Experiments show that the proposed approach is able to handle a multi-objective reward comprised of maximising product sales and minimising wastage of perishable products.
  arXiv  Detail & Related papers  (2020-06-07T04:02:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.