Valuing carbon quota assets of power generation companies based on Lasso-Back propagation neural network

Carbon quota assets have become an increasingly important new type of asset in the production and operation of power generation companies, and evaluating carbon quota assets for the sustainable development of power generation companies is an urgent issue. Herein, we propose a method for evaluating carbon quota assets based on the Lasso- Back Propagation Neural Network model (Lasso-BPNN). Firstly, we further consider the impact of company operations on the value of carbon quota assets, and analyze the ways in which company size, profitability and emission reduction capacity affect the value of carbon quota assets. Secondly, we innovatively introduce intelligent algorithms into the field of carbon asset value assessment, scientifically reflecting the function mapping between carbon quota assets value and influencing factors, and build a Lasso-BPNN model to improve the accuracy of carbon quota asset value assessment. Finally, by valuing the carbon quota assets of company H in the secondary market of the Hubei pilot, power generation companies can improve their carbon quota assets value in terms of three aspects: company size, profitability, and emission reduction capacity. The study provides an effective way to assess the value of carbon quota assets and optimize the carbon assets management of power generation companies.

Automated summary

Carbon quota assets have become increasingly important in power generation companies, and evaluating their value is crucial for sustainable development. This study proposes a method for evaluating carbon quota assets using the Lasso-Back Propagation Neural Network model. It considers the impact of company operations on the value of carbon quota assets and introduces intelligent algorithms to improve accuracy. By valuing carbon quota assets in the secondary market, power generation companies can optimize their carbon assets management.