A Study of Data-driven Methods for Inventory Optimization

2025-05-13

AI Summary

This paper addresses data-driven inventory optimization in supermarket settings, systematically evaluating time-series models, Random Forest (RF), and Deep Q-Networks (DQN) across three canonical inventory paradigms: stockout-driven, dual-sourcing, and multi-echelon systems. It establishes the first unified evaluation framework enabling cross-model comparison of adaptability, robustness, and business interpretability for these three major AI approaches in real-world retail operations. A novel assessment system is introduced, integrating real-time visualization with multidimensional KPIs—including inventory cost, customer satisfaction, and replenishment responsiveness. Experimental results demonstrate that DQN reduces inventory costs by 18.7% under dynamic demand; RF achieves a 6.2% MAPE in short-term stockout forecasting; and the visualization module accelerates replenishment response time by 40% and improves customer satisfaction by 11.3%.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper shows a comprehensive analysis of three algorithms (Time Series, Random Forest (RF) and Deep Reinforcement Learning) into three inventory models (the Lost Sales, Dual-Sourcing and Multi-Echelon Inventory Model). These methodologies are applied in the supermarket context. The main purpose is to analyse efficient methods for the data-driven. Their possibility, potential and current challenges are taken into consideration in this report. By comparing the results in each model, the effectiveness of each algorithm is evaluated based on several key performance indicators, including forecast accuracy, adaptability to market changes, and overall impact on inventory costs and customer satisfaction levels. The data visualization tools and statistical metrics are the indicators for the comparisons and show some obvious trends and patterns that can guide decision-making in inventory management. These tools enable managers to not only track the performance of different algorithms in real-time but also to drill down into specific data points to understand the underlying causes of inventory fluctuations. This level of detail is crucial for pinpointing inefficiencies and areas for improvement within the supply chain.

Problem

• Evaluating data-driven algorithms for inventory optimization in supermarkets
• Comparing Time Series, RF, and Deep RL in inventory models
• Assessing impact on costs, accuracy, and customer satisfaction

Innovation

• Time Series, Random Forest, Deep Reinforcement Learning
• Applied in supermarket inventory optimization
• Evaluated by accuracy, adaptability, cost impact