Listed company ESG evaluation method

Abstract

The invention relates to the technical field of ESG evaluation, in particular to a listed company ESG evaluation method, which comprises the following steps of: establishing a set of weighted total scores of ESG evaluation layer by layer by taking underlying basic data as an entry point and through weight distribution and data identification four-level indexes, and rating according to the weighted total scores. AI, language recognition and other means are adopted in the weighting calculation and rating process to ensure the data accuracy, then the final data accuracy is ensured, and a scientific and accurate strategy basis is provided for ESG investment.

Description

Technical Field

[0001] The present invention relates to the technical field of ESG evaluation, and in particular to an ESG evaluation method for listed companies. Background Art

[0002] ESG stands for Environmental, Social and Governance (ESG), which includes three aspects: a company's impact on the environment, its responsibility to society, and its internal governance. It is used by companies to regulate and monitor their own behavior. It is also the basis for investors to measure the sustainability of the companies or assets they invest in. It is also one of the important strategies used internationally for institutional investors' decision-making principles.

[0003] With the emphasis on high-quality development of listed companies and the introduction of ESG disclosure guidelines, investors' judgment of listed companies is not limited to traditional financial indicators such as market value, growth ability and profitability. Whether their operations will have a positive or negative impact on the environment and society has gradually become an important consideration. Driven by new investment concepts, ESG investment came into being and has developed rapidly. ESG has gradually developed from a niche investment concept to a mainstream investment field. More and more funds are invested in the ESG field around the world, but there is no mature ESG evaluation method for listed companies in the existing technology.

[0004] Based on the above reasons, the present invention designs an ESG evaluation method for listed companies. The underlying data is weightedly calculated through the hierarchical analysis method to obtain the ESG total score and set the letter rating accordingly, thereby giving objective and accurate ESG evaluation results for listed companies and providing a reliable reference for financial institutions. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an ESG evaluation method for listed companies. The underlying data is weightedly calculated through the hierarchical analysis method to obtain the ESG total score and set letter ratings accordingly, thereby giving objective and accurate ESG evaluation results for listed companies and providing a reliable reference for financial institutions.

[0006] In order to achieve the above object, the present invention provides an ESG evaluation method for listed companies, comprising the following steps: S1, build an ESG evaluation system, set ESG indicators and corresponding weights at each level, and review the evaluation system every year; S2, collect underlying data, which comes from annual reports of listed companies, sustainable development reports, company announcements, and public information from regulatory authorities; Use natural language processing (NLP) technology to identify alternative data, AI extraction and manual review to ensure the accuracy of the underlying data; S3, calculate the underlying indicator scores based on the underlying data, use the hierarchical analysis method to weight different scores, and obtain the fourth-level, third-level, second-level, first-level indicator scores and the ESG weighted total score; S4, the final ESG score is obtained based on the ESG weighted total score after industry adjustment and is assigned to the corresponding nine-level letter rating.

[0007] The evaluation system in S1 conducts ratings every quarter.

[0008] Compared with the prior art, the present invention has the following beneficial effects: The present invention adopts a unique algorithm, which has a series of characteristics such as localization, objective quantification, wide coverage, strong timeliness, and significant investment performance. From the evaluation system, the present invention combines international standards, adds Chinese characteristics, and aims to serve asset management institutions. This evaluation system is more independent, neutral and objective; the present invention combines AI extraction and manual review to improve data accuracy, integrates traditional and alternative data, and creates an ESG big data platform. Different industries are suitable for different indicators and weight systems, and the indicator calculation is quantitative and well-founded; at the same time, it has the characteristics of wide coverage and strong timeliness, and can effectively reduce the risk of stepping on thunder. ESG positive screening strategy can improve the performance of the index. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0010] The present invention will now be further described with reference to the accompanying drawings.

[0011] like Figure 1 As shown, the present invention provides an ESG evaluation method for listed companies, comprising the following steps: S1, build an ESG evaluation system, set ESG indicators and corresponding weights at each level, and review the evaluation system every year; S2, collect underlying data, which comes from annual reports of listed companies, sustainable development reports, company announcements, and public information from regulatory authorities; Use natural language processing (NLP) technology to identify alternative data, AI extraction and manual review to ensure the accuracy of the underlying data; S3, calculate the underlying indicator scores based on the underlying data, use the hierarchical analysis method to weight different scores, and obtain the fourth-level, third-level, second-level, first-level indicator scores and the ESG weighted total score; S4, the final ESG score is obtained based on the ESG weighted total score after industry adjustment and is assigned to the corresponding nine-level letter rating.

[0012] The evaluation system in S1 conducts ratings every quarter.

[0013] The ESG level 1, 2 and 3 indicators in this invention are as follows: There are three first-level indicators: environment (E), society (S) and corporate governance (G).

[0014] The 16 secondary indicators are: climate change, resource utilization, environmental pollution, environmental friendliness, environmental management, human capital, product responsibility, suppliers, social contribution, data security and privacy, shareholders' rights and interests, governance structure, information disclosure quality, governance risks, external sanctions, and business ethics.

[0015] The 44 third-level indicators are: greenhouse gas emissions, carbon reduction routes, climate change response, sponge cities, green finance, land use and biodiversity, water consumption, material consumption, industrial emissions, hazardous waste, electronic waste, renewable energy, green buildings, green factories, sustainable certification, supply chain management-E, environmental penalties, employee health and safety, employee incentives and development, employee relations, quality certification, recalls, complaints, supplier risks and management, supply chain relationships, inclusiveness, community investment, employment, technological innovation, data security and privacy, shareholder rights protection, ESG governance, risk control, board structure, management stability, ESG external assurance, credibility of information disclosure, behavior of major shareholders, debt repayment ability, legal proceedings, tax transparency, external sanctions, business ethics, and anti-corruption and bribery.

[0016] Each indicator is scored out of 100 points. The third-level indicator score is calculated by multiplying the fourth-level indicator score to which it belongs by the corresponding weight, and so on, to obtain the second-level indicator score, the first-level indicator score and the ESG weighted total score. The ESG total score is adjusted for the industry to obtain the final ESG score, which is then divided into 9 letter ratings (AAA-C).

[0017] We take the two indicators of greenhouse gas emissions (quantitative) and climate change response (qualitative) of A-share listed companies in the 20240430 evaluation period as examples to show how we evaluate the ESG performance of listed companies: Collect the 2023 ESG reports and annual reports issued by all A-share companies listed as of April 30, 2024; For greenhouse gas quantitative indicators, AI is first used to extract several underlying quantitative data related to greenhouse gas emission indicators (greenhouse gas emission range 1 / 2 / 3), and then the original data is manually checked and reviewed, and then a third person conducts horizontal and vertical trend inspections; For qualitative indicators of risk climate response, natural language text analysis is used to identify and extract relevant content, and then the extracted text is layered according to the depth of the content to facilitate subsequent layered scoring; Through steps (2) and (3), we have collected the underlying data, input the underlying data into our scoring model, output the scores of all companies on these two indicators (out of 100 points), and finally conduct random checks to verify whether the scores are correct.

[0018] The above are only preferred embodiments of the present invention, which are only used to help understand the method and core ideas of the present application. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

[0019] The present invention solves the deficiency in the prior art that there is no mature ESG evaluation method for listed companies as a whole. It constructs a set of four-level indicators with underlying basic data as the entry point, obtains the weighted total score of ESG evaluation layer by layer through weight allocation and data identification, and uses it for rating. The weighted calculation and rating process adopts AI and language recognition to ensure data accuracy, thereby ensuring the final data accuracy, providing a scientific and accurate strategic basis for ESG investment.

Claims

1. A method for evaluating ESG of listed companies, characterized in that: The following steps are involved: S1, build an ESG evaluation system, set ESG indicators and corresponding weights at each level, and review the evaluation system every year; S2, collect underlying data, which comes from annual reports of listed companies, sustainable development reports, company announcements, and public information from regulatory authorities; Use natural language processing (NLP) technology to identify alternative data, AI extraction and manual review to ensure the accuracy of the underlying data; S3, calculate the underlying indicator scores based on the underlying data, and use the hierarchical analysis method to weight different scores to obtain the fourth-level, third-level, second-level, first-level indicator scores and the ESG weighted total score; S4. The final ESG score is obtained based on the ESG weighted total score after industry adjustment and is assigned to the corresponding nine-level letter rating.

2. The ESG evaluation method for listed companies according to claim 1, characterized in that: The evaluation system in S1 is rated every quarter.

Images