Dağ, HasanColhak,F.Ucar,B.E.Saygut,I.Duzgun,B.Demirkiran,F.Dag,H.2024-06-232024-06-2320230979-835034081-5https://doi.org/10.1109/UBMK59864.2023.10286707https://hdl.handle.net/20.500.12469/5841Despite their potential business value and invest-ments, data science projects often fail owing to a lack of preparedness, implementation challenges, and poor data quality. This study aimed to develop a machine learning model for predicting defective products in the dyeing process within the manufacturing domain. However, inadequate importance given to data by the involved factory, insufficient data quality, and the lack of the necessary technical infrastructure for data science projects have hindered attaining desired results. This study emphasizes to academic researchers and industry experts the significance of data quality and technical infrastructure, highlights how these deficiencies can impact the success of a data science project, and provides several recommendations. © 2023 IEEE.eninfo:eu-repo/semantics/closedAccessdata qualitydata scienceimbalanced datamachine learningmanufacturingConference Object28228710.1109/UBMK59864.2023.102867072-s2.0-85177602126N/AN/A