Retail demand forecasting is evolving from static prediction models into dynamic decision systems that must continuously adapt to changing market conditions. Traditional approaches often rely on isolated data pipelines and linear models, limiting their ability to capture complex relationships across products, locations, customer behavior, and external signals. As a result, forecasting systems struggle to provide context aware and explainable decisions at scale.
This session introduces a graph powered approach to retail forecasting, where AI agents operate on top of a knowledge graph to enable context aware decision making. By structuring demand signals such as historical sales, promotions, pricing changes, regional variations, weather patterns, and supply constraints into a connected graph, the system captures relationships that are not visible in traditional tabular models. This graph serves as a shared memory layer that AI agents can query, reason over, and continuously update.
The proposed architecture combines three key components: a signal processing layer that transforms raw inputs into graph representations, a graph based context layer that encodes relationships and dependencies, and an agent layer that uses this structured context to generate forecasts, recommend actions, and explain outcomes. Using graph driven retrieval and reasoning, these agents move beyond prediction to support scenario evaluation, root cause analysis, and adaptive decision making.
The session will demonstrate how graph based AI systems improve forecasting accuracy, enhance explainability, and enable faster response to demand shifts. It will also highlight how integrating graph memory with agent workflows reduces fragmentation across merchandising, supply chain, and operations teams.
Attendees will gain practical insights into designing context aware AI systems using graphs and agents, along with a roadmap for transitioning from traditional forecasting pipelines to intelligent, connected decision platforms.
Speaker
Mazdul Choudhury
Staff Product Manager, Walmart Inc
Mazdul Hassan Choudhury is a Product Management leader with over 15 years of experience delivering digital products across retail operations, supply chain, merchandising, fulfillment, last-mile delivery, and customer care. He has led the development and launch of enterprise products that improved operational efficiency, increased revenue, and enhanced customer experience.
He currently serves as a Staff Product Manager at Walmart, where he owns and manages associate-facing applications and aligns product roadmaps with enterprise strategy. His work includes launching a GenAI-powered tool that improved operational efficiency, redesigning onboarding processes to reduce onboarding time by 80%, and delivering solutions that improved fulfillment accuracy and supported large-scale pre-order operations.
Prior to Walmart, Mazdul worked at Bob’s Furniture, where he led the development of a mobile point-of-sale system used by 3,500 associates, increasing sales by 20% and reducing order processing time. He also built a customer relationship management platform that improved customer satisfaction and developed analytics solutions that increased operational visibility.
Earlier in his career, he held roles at Capgemini, Equinor, and IBM, where he managed cross-functional teams and delivered SAP implementations, system integrations, and large-scale technology projects.
He holds an MBA in Strategy and Operations and a Master’s degree in Information Systems Management from Boston University, along with a Bachelor’s degree in Electronics and Communication Engineering.
