{"683086":{"#nid":"683086","#data":{"type":"news","title":"Georgia Tech AI Tool Cuts Supply Chain Planning from Hours to Minutes","body":[{"value":"\u003Cp\u003EResearchers at Georgia Tech have developed a new artificial intelligence tool that dramatically improves how companies plan their supply chains, cutting down the time and cost it takes to generate complex production and inventory schedules.\u0026nbsp;\u003C\/p\u003E\u003Cp\u003EThe tool, known as PROPEL, combines machine learning with optimization techniques to help manufacturers make better decisions in less time. It was created by researchers at the \u003Ca href=\u0022https:\/\/www.ai4opt.org\/\u0022\u003ENSF AI Institute for Advances in Optimization\u003C\/a\u003E, or AI4OPT, based at \u003Ca href=\u0022https:\/\/gatech.edu\/\u0022\u003EGeorgia Tech\u003C\/a\u003E under \u003Ca href=\u0022http:\/\/ai.gatech.edu\/\u0022\u003ETech AI\u003C\/a\u003E (the AI Hub at Georgia Tech).\u003C\/p\u003E\u003Cp\u003EThe technology is already being tested on real-world supply chain data provided by \u003Ca href=\u0022https:\/\/www.kinaxis.com\/\u0022\u003EKinaxis\u003C\/a\u003E, a Canada-based company that supplies planning software to global manufacturers in industries ranging from automotive to consumer goods.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.linkedin.com\/in\/vahid-eghbal-akhlaghi-961854344\u0022\u003EVahid Eghbal Akhlaghi\u003C\/a\u003E, senior research scientist at Kinaxis and former postdoctoral fellow at AI4OPT and the \u003Ca href=\u0022https:\/\/www.isye.gatech.edu\/\u0022\u003EH. Milton Stewart School of Industrial and Systems Engineering\u003C\/a\u003E (ISyE) at Georgia Tech, said, \u201cOur industry partner has been instrumental in shaping PROPEL\u2019s capabilities. By validating the approach with real operational data, we ensured it addresses true bottlenecks in supply chain planning.\u201d\u003C\/p\u003E\u003Cp\u003E\u0022PROPEL represents a leap forward in how we tackle massive, complex planning problems,\u0022 said \u003Ca href=\u0022https:\/\/ai.gatech.edu\/node\/21324\u0022\u003EPascal Van Hentenryck\u003C\/a\u003E, lead researcher, the director of Tech AI and the NSF AI4OPT Institute, and the A. Russell Chandler III Chair and Professor at Georgia Tech with appointments in the colleges of engineering and computing. \u0022By combining supervised and reinforcement learning, we can make near-optimal industrial-scale decisions, an order of magnitude faster.\u0022\u003C\/p\u003E\u003Cp\u003ETraditional supply chain planning problems are typically solved using mathematical models that require immense computing power\u2014often too much to meet real-time business needs. PROPEL, short for Predict-Relax-Optimize using LEarning, reduces this burden by teaching the AI model to first eliminate irrelevant decisions and then fine-tune the solution to meet quality standards.\u003C\/p\u003E\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.isye.gatech.edu\/users\/reza-zandehshahvar\u0022\u003EReza\u0026nbsp;Zandehshahvar\u003C\/a\u003E, one of the paper\u2019s co-authors and postdoctoral fellow with the NSF AI4OPT and the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) at Georgia Tech, said the breakthrough lies not just in the AI algorithms but in how they\u0027re trained and deployed at scale.\u003C\/p\u003E\u003Cp\u003E\u201cMany AI models struggle when applied to problems with millions of variables. PROPEL was built from the ground up to handle industrial complexity, not just academic examples,\u201d Zandehshahvar said. \u201cWe\u2019re seeing real improvements in both solution speed and quality.\u201d\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;In trials using Kinaxis\u2019 historical industrial data, PROPEL achieved an 88% reduction in the time needed to find a high-quality plan and improved solution accuracy by more than 60% compared to conventional methods.\u003C\/p\u003E\u003Cp\u003EWhile many AI methods in supply chain rely on simulated data or simplified models, PROPEL\u2019s performance has been validated using real-world scenarios, ensuring its reliability in high-stakes operational settings.\u003C\/p\u003E\u003Cp\u003EThe Georgia Tech team says PROPEL could benefit industries that manage large, multi-tiered production networks, including pharmaceuticals, electronics, and heavy manufacturing. The researchers are now exploring partnerships with additional companies to deploy PROPEL in live environments.\u003C\/p\u003E\u003Cp\u003EAccess the abstract on \u003Ca href=\u0022https:\/\/arxiv.org\/abs\/2504.07383\u0022\u003EarXiv\u003C\/a\u003E.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EResearchers at Georgia Tech have developed a new artificial intelligence tool that dramatically improves how companies plan their supply chains, cutting down the time and cost it takes to generate complex production and inventory schedules.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"PROPEL, a new AI tool combines machine learning with optimization techniques to help manufacturers make better decisions in less time."}],"uid":"36348","created_gmt":"2025-07-10 14:39:10","changed_gmt":"2025-08-29 14:42:42","author":"Breon Martin","boilerplate_text":"","field_publication":"","field_article_url":"","location":"Atlanta, GA","dateline":{"date":"2025-07-10T00:00:00-04:00","iso_date":"2025-07-10T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"677380":{"id":"677380","type":"image","title":"Georgia Tech AI Tool Cuts Supply Chain Planning from Hours to Minutes Article Image","body":null,"created":"1752158373","gmt_created":"2025-07-10 14:39:33","changed":"1752158373","gmt_changed":"2025-07-10 14:39:33","alt":"Georgia Tech AI Tool Cuts Supply Chain Planning from Hours to Minutes Article Image","file":{"fid":"261274","name":"PROPEL-IMAGE.png","image_path":"\/sites\/default\/files\/2025\/07\/10\/PROPEL-IMAGE.png","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/2025\/07\/10\/PROPEL-IMAGE.png","mime":"image\/png","size":3094480,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/2025\/07\/10\/PROPEL-IMAGE.png?itok=Dtbjafx4"}}},"media_ids":["677380"],"groups":[{"id":"155831","name":"Georgia Tech Manufacturing Institute (GTMI)"},{"id":"1188","name":"Research Horizons"}],"categories":[{"id":"194609","name":"Industry"}],"keywords":[{"id":"192863","name":"go-ai"},{"id":"187915","name":"go-researchnews"},{"id":"186857","name":"go-gtmi"}],"core_research_areas":[{"id":"193655","name":"Artificial Intelligence at Georgia Tech"},{"id":"39461","name":"Manufacturing, Trade, and Logistics"}],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EBreon Martin\u003C\/p\u003E\u003Cp\u003EAI Marketing Communications Manager\u003C\/p\u003E","format":"limited_html"}],"email":["breon@gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}