Research on COE Program with Machine Learning Algorithms

Jiashi Li

2022

Abstract

The market price of COE coffee depends on its heterogeneity characteristics, and hedonic model theory is the dominant research approach for coffee prices. In this paper, the correlation between coffee prices and the New York C-futures index is first verified. Further, machine learning algorithms such as Support Vector Regression (SVR), Multilayer Perceptron (MLP) models are used to study the factors affecting prices. A more general coding of coffee types is designed and improved the one-hot coding of the regression model. The performance shows that the improved model is better in terms of performance. The prediction accuracy of the model improved by 24.65% after generalized coding of coffee categories. The study further explores the implementation of the hedonic pricing theory.

Paper Citation

in Harvard Style

Li J. (2022). Research on COE Program with Machine Learning Algorithms. In Proceedings of the International Conference on Big Data Economy and Digital Management - Volume 1: BDEDM, ISBN 978-989-758-593-7, pages 563-568. DOI: 10.5220/0011191800003440

in Bibtex Style

@conference{bdedm22,
author={Jiashi Li},
title={Research on COE Program with Machine Learning Algorithms},
booktitle={Proceedings of the International Conference on Big Data Economy and Digital Management - Volume 1: BDEDM,},
year={2022},
pages={563-568},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011191800003440},
isbn={978-989-758-593-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the International Conference on Big Data Economy and Digital Management - Volume 1: BDEDM,
TI - Research on COE Program with Machine Learning Algorithms
SN - 978-989-758-593-7
AU - Li J.
PY - 2022
SP - 563
EP - 568
DO - 10.5220/0011191800003440