ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Machine Learning-based Analysis of Correlation between Energy Consumption Data of the Company and its Sales
Cited 0 time in scopus Download 4 time Share share facebook twitter linkedin kakaostory
저자
이준기, 김낙우, 이현용, 박상준, 이병탁
발행일
202010
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2020, pp.1258-1260
DOI
https://dx.doi.org/10.1109/ICTC49870.2020.9289575
협약과제
20PK1100, 전력 빅데이터를 활용한 신산업 BM 및 서비스 개발·검증, 이병탁
초록
This paper has researched about the correlation between company data, and its annual sales data. Using the identified correlation, we propose a new method of predicting the company's annual sales data with energy consumption data. For this work, gradient boosting was applied to the predictive learning model for effective and better performance of prediction. To implement this method, district address-based energy consumption data is merged into company survey data with pre-processing. Then to predict the sales of each company, the gradient boosting based machine learning model has applied. Our approach to utilizing the energy consumption data can contribute to a new method of predicting the status of companies.
KSP 제안 키워드
Company data, Company survey, Learning model, Learning-based, Performance of prediction, Pre-processing, Sales data, consumption data, energy consumption, gradient boosting, machine Learning