{"id":478,"date":"2023-08-14T22:13:04","date_gmt":"2023-08-14T15:13:04","guid":{"rendered":"http:\/\/www.dbs.grad.chula.ac.th\/wp\/?p=478"},"modified":"2026-09-17T10:56:37","modified_gmt":"2026-09-17T03:56:37","slug":"top-10-machine-learning-application-in-retail","status":"publish","type":"post","link":"http:\/\/www.dbs.grad.chula.ac.th\/wp\/?p=478","title":{"rendered":"Top 10 Machine Learning Application in Retail"},"content":{"rendered":"

\"machine<\/p>\n

Deep learning models can be difficult to interpret, making it hard to understand why a model made a specific prediction. Cybersecurity and data privacy are currently US executives’ top concerns when implementing generative AI, at 81% and 78% respectively (Itransition, 2025). Many retailers operate on outdated infrastructures that do not seamlessly support ML integration, leading to downtime and workflow disruptions (Devfi, February 18, 2025). ML models consistently outperform traditional statistical methods when exogenous factors (weather, events, prices) are present, especially when feature engineering addresses nonlinearity (ResearchGate, December 25, 2023, citing Makridakis et al., 2018). Traditional retailers are rapidly catching up\u2014Target’s digital business growth, particularly through same-day fulfillment services, drove Q revenue performance improvements (AIM Media House, June 23, 2024).<\/p>\n<\/p>\n