Predicting the customer of cafeteria using unstructured data

• 영문명: Predicting the customer of cafeteria using unstructured data
• 발행기관: 한국자료분석학회
• 저자명: Kyeongjun Lee
• 간행물 정보: 『한국자료분석학회 학술대회자료집』2023년 동계학술대회 발표집, 303~305쪽, 전체 3쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2023.12.31

국문 초록

This study aimed to predict the number of meals served in a group cafeteria using machine learning techꠓnology. Menu feature variables were created through the Word2Vec technique and clustering, and a stacking ensemble model was constructed using Random Forest, Gradient Boosting, and Cat Boost as sub-models. Reꠓsults showed that Cat Boost had the best performance, and the ensemble model showed an 8% improvement in performance. The study also found that the date factor had the greatest influence on the number of diners in a cafeteria, followed by menu characteristics and other factors. The implications of the study include the potenꠓtial for machine learning technology to improve predictive performance and reduce food waste, as well as the removal of subjective elements in menu classification. Limitations of the research include limited data cases and a weak model structure when new menus or foreign words are not included in the learning data. Future studies should aim to address these limitations.

키워드

Ensemble model machine learning food waste prediction word embedding