首页|基于SSA—BP机器学习模型的新能源上市企业价值评估研究

基于SSA—BP机器学习模型的新能源上市企业价值评估研究

扫码查看
新能源产业是实现我国"双碳"目标的重要领域,新能源上市企业是能源革命的生力军.目前新能源企业价值评估存在评估过程复杂、相关评估方法自洽性较弱等问题.本文整理了 2018-2022 年 60 家新能源上市企业的相关数据,在Spearman相关性分析以及偏相关分析的基础上,建立了新能源上市企业价值评估指标体系.同时,依据SSA算法与BP神经网络智能化原理,构建并验证了SSA-BP机器学习模型的可行性和有效性.研究表明,SSA-BP机器学习模型能较好地反映新能源上市企业价值.因此,建议强化营运资金数字化管理、加大科技创新投入、升级跨境新能源产业链布局"补链强链"、充分发挥有效市场和有为政府的双重作用,助力新能源上市企业高质量发展.
Research on Value Assessment of New Energy Listed Enterprises Based on SSA-BP Machine Learning Models
New energy industry is an important field for realizing China's"double carbon"goal,and new energy listed enterprises are the driving force of the energy revolution and ushering in the window of development for improving quality and efficiency.At present,the value assessment of new energy enterprises exists problems such as complicated assessment process and weak self-consistency of relevant assessment methods.This paper collates the relevant data of 60 new energy listed enterprises from 2018 to 2022,and establishes a new energy listed enterprise value assessment index system based on Spearman correlation analysis and partial correlation analysis.At the same time,based on the SSA algorithm and the principle of BP neural network intelligence,the feasibility and effectiveness of the SSA-BP machine learning model are constructed and verified.The study shows that the SSA-BP machine learning model can better reflect the value of new energy listed enterprises.Therefore,it is recommended to strengthen the digital management of working capital,increase the investment in scientific and technological innovation,upgrade the layout of cross-border new energy industry chain,and give full play to the dual roles of the effective market and the active government to help new energy-listed enterprises develop in a high-quality manner.

New energySSA algorithmBP neural networkValue assessment

谢非、赵文婷

展开 >

重庆理工大学经济金融学院,重庆 400054

新能源 SSA算法 BP神经网络 价值评估

国家社会科学基金重点项目

23AJY023

2024

中国资产评估
中国资产评估协会

中国资产评估

CSTPCDCHSSCD
影响因子:0.164
ISSN:1007-0265
年,卷(期):2024.(5)
  • 21