2026-09-19T05:24:42Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1271042026-06-06T01:04:09Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Tugba Efendigil. Teo, William W. J. Massachusetts Institute of Technology. Supply Chain Management Program. Massachusetts Institute of Technology. Supply Chain Management Program 2020-09-03T17:47:07Z 2020-09-03T17:47:07Z 2020 2020 https://hdl.handle.net/1721.1/127104 1191824525 Thesis: M. Eng. in Supply Chain Management, Massachusetts Institute of Technology, Supply Chain Management Program, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 74-80). Information sharing is one of the established approaches to improve demand forecasting and reduce the bullwhip effect, but it is infeasible to do so effectively in a long supply chain. Using the polystyrene industry as a case study, this thesis explores the usage of modern natural language processing (NLP) techniques in a deep learning model, known as NEMO, to forecast the demand of a commodity -- without requiring downstream companies to share information. In addition, this thesis compares the effectiveness of such an approach with other non-deep learning approaches, specifically an ARIMA model and a gradient boosting model, XGBoost, to demand forecasting. All three models returned large forecast errors. However, NEMO tracked the volatility of actual data better than the ARIMA model. NEMO also had better success in predicting demand than the XGBoost model, returning approximately 20% better Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores. This result suggests that NEMO can be improved with better data, but other issues, such as legality of text mining, need to be considered and addressed before NEMO can be used in day-to-day operations. In its current form, NEMO can be used alongside other forecasting models and provide invaluable information about upcoming demand volatility. by William W.J. Teo. M.Eng. in Supply Chain Management M.Eng.inSupplyChainManagement Massachusetts Institute of Technology, Supply Chain Management Program 80 pages eng Massachusetts Institute of Technology MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 Supply Chain Management Program. A natural language processing approach to improve demand forecasting in long supply chains Thesis application/pdf 2020-09-03T17:47:06Z Publication Master SCM unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1a208a1a-9a78-4f57-a7b9-bc81979f7cd2"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>A natural language processing approach to improve demand forecasting in long supply chains</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Teo, William W. J.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Supply Chain Management Program.</Keyword> <Abstract>Information sharing is one of the established approaches to improve demand forecasting and reduce the bullwhip effect, but it is infeasible to do so effectively in a long supply chain. Using the polystyrene industry as a case study, this thesis explores the usage of modern natural language processing (NLP) techniques in a deep learning model, known as NEMO, to forecast the demand of a commodity -- without requiring downstream companies to share information. In addition, this thesis compares the effectiveness of such an approach with other non-deep learning approaches, specifically an ARIMA model and a gradient boosting model, XGBoost, to demand forecasting. All three models returned large forecast errors. However, NEMO tracked the volatility of actual data better than the ARIMA model. NEMO also had better success in predicting demand than the XGBoost model, returning approximately 20% better Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) scores. This result suggests that NEMO can be improved with better data, but other issues, such as legality of text mining, need to be considered and addressed before NEMO can be used in day-to-day operations. In its current form, NEMO can be used alongside other forecasting models and provide invaluable information about upcoming demand volatility.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>