CN116664016A - Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium - Google Patents
Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116664016A CN116664016A CN202310930970.0A CN202310930970A CN116664016A CN 116664016 A CN116664016 A CN 116664016A CN 202310930970 A CN202310930970 A CN 202310930970A CN 116664016 A CN116664016 A CN 116664016A
- Authority
- CN
- China
- Prior art keywords
- sub
- target
- esg
- topics
- topic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012216 screening Methods 0.000 title claims abstract description 42
- 230000008569 process Effects 0.000 abstract description 15
- 238000007405 data analysis Methods 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a screening method and device of ESG (electronic service guide) sub issues, electronic equipment and a readable storage medium, and belongs to the technical field of data analysis. The method comprises the following steps: acquiring a plurality of ESG rating reports; selecting a plurality of sub-topics to be screened and topic scores corresponding to the plurality of sub-topics to be screened from the ESG rating reports; based on the scores of the plurality of sub-subjects to be screened and the questions, a plurality of common factors influencing the ESG rating result are induced from the plurality of sub-subjects to be screened, contribution degrees corresponding to the common factors are obtained, the contribution degrees are used for representing the influence degree of the corresponding common factors on the ESG rating result, and each common factor corresponds to part of the sub-subjects in the plurality of sub-subjects to be screened; determining a target factor from the plurality of commonality factors based on a preset contribution threshold and contribution degrees corresponding to the commonality factors; and determining a part of sub-topics corresponding to the target factors as target sub-topics. The method simplifies the rating process and is convenient for the implementation of ESG rating.
Description
Technical Field
The application belongs to the technical field of data analysis, and particularly relates to a screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and a readable storage medium.
Background
Environmental, social and corporate governance (Environmental Social and Governance, ESG) generally refers to the assessment of the sustainability of corporate operations and the impact on social value ideas from three dimensions of environmental, social and corporate governance.
The ESG rating method is basically 'weighted summation', namely, aiming at different industries, different weights are set for three aspects of environment, society and company management, more sub-issues are set at the lower level, and after the sub-issue scores are obtained, weighted summation is carried out to obtain the whole ESG scores. However, in the existing ESG rating process, the number and dimensions of the designed sub-topics are complex, and there are cases that the company cannot provide corresponding data, and the rating process is also more complex, so that the implementation of ESG rating is inconvenient.
Disclosure of Invention
An object of the embodiments of the present application is to provide a screening method, apparatus, electronic device and readable storage medium for ESG sub-issues, which can solve the problem that the conventional ESG rating method is inconvenient to implement.
In a first aspect, an embodiment of the present application provides a method for screening ESG subtopics, where the method includes:
acquiring a plurality of ESG rating reports;
selecting a plurality of sub-topics to be screened from the ESG rating reports and scoring corresponding to the sub-topics to be screened respectively;
based on the plurality of sub-subjects to be screened and the subject scores, a plurality of common factors influencing the ESG rating results are induced from the plurality of sub-subjects to be screened, and contribution degrees corresponding to the common factors are obtained, wherein the contribution degrees are used for representing the influence degree of the corresponding common factors on the ESG rating results, and each common factor corresponds to part of the sub-subjects in the plurality of sub-subjects to be screened;
determining a target factor from the plurality of commonality factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of commonality factors;
and determining a part of sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened.
Optionally, in the case that the number of the target factors is a plurality of, a sum of contribution degrees corresponding to the target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
Optionally, the determining, from the sub-topics to be screened, a partial sub-topic corresponding to the target factor as a target sub-topic includes:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
Optionally, after determining, from the sub-topics to be screened, a part of the sub-topics corresponding to the target factor as target sub-topics, the method further includes:
and determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic.
Optionally, the determining the ESG rating result based on the target sub-topic and the topic score corresponding to the target sub-topic includes:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
In a second aspect, an embodiment of the present application provides a screening apparatus for ESG subissues, where the apparatus includes:
the first acquisition module is used for acquiring a plurality of ESG rating reports;
a selecting module, configured to select a plurality of sub-topics to be screened from the plurality of ESG rating reports and topic scores corresponding to the plurality of sub-topics to be screened;
the second obtaining module is configured to sum up a plurality of commonality factors having an influence on the ESG rating result from the plurality of sub-topics to be screened based on the plurality of sub-topics to be screened and the topic score, and obtain contribution degrees corresponding to the commonality factors, where the contribution degrees are used to characterize the influence degree of the corresponding commonality factors on the ESG rating result, and each of the commonality factors corresponds to a part of sub-topics in the plurality of sub-topics to be screened;
the first determining module is used for determining a target factor from the plurality of commonality factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of commonality factors;
and the second determining module is used for determining a part of sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened.
Optionally, in the case that the number of the target factors is a plurality of, a sum of contribution degrees corresponding to the target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
Optionally, the second determining module is further configured to:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
Optionally, the apparatus further includes a rating module for determining an ESG rating result based on the target sub-topic and the topic score corresponding to the target sub-topic.
Optionally, the evaluation module is further configured to:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes a processor and a memory, where the memory stores a program or instructions executable on the processor, and the program or instructions implement the steps of the method for screening ESG sub-topics according to the first aspect when executed by the processor.
In a fourth aspect, an embodiment of the present application provides a readable storage medium, where a program or an instruction is stored, where the program or the instruction implements the steps of the method for screening ESG sub-topics according to the first aspect when executed by a processor.
In the embodiment of the application, a plurality of sub-subjects to be screened and subject scores corresponding to each sub-subject to be screened are selected from a plurality of ESG rating reports, and a commonality factor and a contribution degree corresponding to the commonality factor are induced according to the sub-subjects to be screened and the subject scores; determining a target factor according to the relation between the contribution degree corresponding to the commonality factor and the preset contribution degree; according to the target factors, the target sub-subjects are determined from the sub-subjects to be screened, other sub-subjects except the target sub-subjects are removed, and in the subsequent ESG rating process, only data corresponding to the target sub-subjects are required to be collected to obtain an ESG rating result, so that the collection difficulty of data required by the ESG rating process is reduced, the rating process is simplified, and the implementation of ESG rating is facilitated.
Drawings
Fig. 1 is a flowchart of a method for screening ESG subtopics according to an embodiment of the present application;
fig. 2 is a second flowchart of a method for screening ESG subtopics according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a screening device for ESG subtopics provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The method provided by the embodiment of the application is described in detail through specific embodiments and application scenes thereof with reference to the accompanying drawings.
Fig. 1 is a flowchart of a method for screening ESG sub-topics, as shown in fig. 1, where the method for screening ESG sub-topics provided in the embodiment of the present application includes the following steps:
step S1, a plurality of ESG rating reports are obtained,
the plurality of ESG rating reports may be ESG rating reports corresponding to all listed companies in the same industry, where the ESG rating includes three major dimensions of environment, society and corporate governance, and each dimension may include a plurality of sub-issues. For example, the environment dimensions may include: carbon emissions, water resource pressure, biodiversity and land utilization, hazardous emissions and waste, etc., the social dimensions may include: product security and quality, privacy and data security, chemical security, consumer finance protection, community relationships, etc., corporate governance dimensions may include: supply chain labor standard, labor management, human resource development, controversial purchasing, etc. The choice of sub-topics is different for companies in different industries. Based on the actual situation of each sub-topic in three major dimensions of environment, society and company governance, the topic score corresponding to each sub-topic is determined.
Step S2, selecting a plurality of sub-subjects to be screened from the ESG rating reports and subject scores corresponding to the sub-subjects to be screened respectively,
selecting all the sub-topics considered in the ESG rating reports as the sub-topics to be screened, and obtaining the topic score corresponding to each sub-topic to be screened. It should be noted that the sub-issues to be screened are different in different industries. For example, for the energy industry, sub-issues to be screened are carbon emissions, water resource pressure, biodiversity and land availability, harmful emissions and waste, opportunities in the clean technical field, labor management, human resource development, health and safety, privacy and data security. For example, for the real estate industry, the sub-topics to be screened are water resource pressure, opportunities in the green building field, human resource development, health and safety, product safety and quality, privacy and data safety.
Step S3, based on the plurality of sub-subjects to be screened and the subject scores, a plurality of common factors having influence on the ESG rating results are induced from the plurality of sub-subjects to be screened, contribution degrees corresponding to the common factors are obtained, the contribution degrees are used for representing the influence degree of the corresponding common factors on the ESG rating results, each common factor corresponds to part of the sub-subjects to be screened,
the process of summarizing the common factors may use a factor analysis method, and construct a feature set by using the topic scores corresponding to the plurality of sub-topics to be screened, so as to construct a factor analysis model:
wherein, the liquid crystal display device comprises a liquid crystal display device,p is the vector of dimension p, p is the number of sub-topics to be screened,in order to generalize the commonality factor,for the generalized special factors, the commonality factors represent mutually independent commonality influencing factors which cannot be directly observed but objectively exist in the original variables (sub-topics to be screened); m is the number of commonality factors, m < p;as a matrix of the factor load,and determining according to the sub-subjects to be screened and the corresponding subject scores. It should be noted that, m may be a preset value, or the value of m may be adjusted according to feedback of a subsequent ESG rating result.
Further, solving the factor load matrixThe method comprises the following steps:
1. for a pair ofAnd (3) performing standardization, eliminating the variable dimension difference, wherein the variable mean value is 0, and the variance is 1.
2. Calculating covariance matrix of the sample, and recording asPerforming feature decomposition on the covariance matrix to obtain feature valuesFeature vectorThe factor load matrix is:
3. factor rotation, the coordinate change, makes each original variable as little as possible to generate close relation with the common factor.
4. Will beThe sum of squares of the elements of column j of (a) is noted asCalled commonality factorThe variance contribution to x is calculated by analogy to obtain the variance contribution of all the commonality factors to x.
By the above solution factor load matrixAnd (3) obtaining the variance contribution of each commonality factor to the corresponding sub-subjects to be screened, and determining the variance contribution as the contribution degree corresponding to each commonality factor.
Step S4, determining a target factor from the plurality of common factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of common factors,
the determination mode of the target factor may be: comparing the contribution degree corresponding to each commonality factor with a preset contribution degree threshold value, and selecting a target factor with the corresponding contribution degree larger than or equal to the preset contribution degree threshold value. The determination mode of the target factor may also be: and selecting a plurality of common factors, comparing the sum of contribution degrees corresponding to the selected common factors with a preset contribution degree threshold, and taking the selected common factors as target factors when the sum of the contribution degrees corresponding to the selected common factors is treated or equal to the preset contribution degree threshold.
Step S5, determining a part of sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened.
Each commonality factor corresponds to a part of the sub-topics to be screened, and after the target factors are determined, the part of the sub-topics corresponding to the target factors are determined to be target sub-topics. For example, for the energy industry, the partial sub-topics corresponding to the first target factor are carbon emissions, water resource pressure, the partial sub-topics corresponding to the second target factor are water resource pressure, biodiversity, and land availability, and the target sub-topics are carbon emissions, water resource pressure, biodiversity, and land availability.
In the above step, selecting a plurality of sub-topics to be screened and topic scores corresponding to each sub-topic to be screened from a plurality of ESG rating reports, and inducing commonality factors and contribution degrees corresponding to the commonality factors according to the sub-topics to be screened and topic scores; determining a target factor according to the relation between the contribution degree corresponding to the commonality factor and the preset contribution degree; according to the target factors, the target sub-subjects are determined from the sub-subjects to be screened, other sub-subjects except the target sub-subjects are removed, and in the subsequent ESG rating process, only data corresponding to the target sub-subjects are required to be collected to obtain an ESG rating result, so that the collection difficulty of data required by the ESG rating process is reduced, the rating process is simplified, and the implementation of ESG rating is facilitated.
Optionally, in the case that the number of the target factors is a plurality of, a sum of contribution degrees corresponding to the target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
In an embodiment, after the contribution degree corresponding to each common factor is obtained, n common factors are selected, when the sum of the contribution degrees corresponding to the n common factors is greater than or equal to a preset contribution degree threshold, the n common factors selected at this time are taken as target factors, optionally, the preset contribution degree threshold may be 95%, and since the sum of the contribution degrees of the target factors is greater than the preset contribution degree threshold, the target factors may be considered to be sufficient to restore the whole information amount, and other common factors may be ignored. Further, the sub-topics corresponding to the target factors support ESG ratings, and the sub-topics corresponding to the target factors are determined as target sub-topics. Wherein n is a positive integer.
In another embodiment, after the contribution degree corresponding to each common factor is obtained, sorting each common factor according to the contribution degree, sequentially selecting the common factors from large to small until the sum of the contribution degrees corresponding to the n common factors is greater than or equal to a preset contribution degree threshold, and taking the n common factors selected at this time as target factors. Wherein n is a positive integer. In this embodiment, the commonality factors are selected according to the order from the large contribution degree to the small contribution degree, so that the maximum overall information quantity that the target factors can restore can be ensured, and the accuracy of the ESG rating result determined based on the obtained target sub-issues is ensured.
Optionally, the determining, from the sub-topics to be screened, a partial sub-topic corresponding to the target factor as a target sub-topic includes:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
According to factor load matrixDeterminingSum of squares of i-th row element in (b)，Reflecting the effect of sub-topics on common factors.
After the target factor and the first sub-topic corresponding to the target factor are determined, determining the importance of the first sub-topic to the corresponding target factor based on the sum of squares of i rows of elements of the factor load matrix. When the importance corresponding to the first sub-topic is greater than or equal to a preset importance threshold, determining the first sub-topic as a target sub-topic.
In an embodiment, the preset importance threshold is 0, the first sub-issue with the corresponding importance positive is determined as the target sub-issue, and the first sub-issue with the corresponding importance negative or 0 is eliminated.
In the screening method of the ESG sub-topics in the embodiment, the importance of the first sub-topic is compared with the preset importance, so that part of sub-topics are further removed, the number of sub-topics is reduced, and the implementation of ESG rating is facilitated.
In an alternative embodiment, fig. 2 is a flowchart of a method for screening ESG subtopics, as shown in fig. 2, where the screening method includes the following steps:
step S1, a plurality of ESG rating reports are obtained,
step S2, selecting a plurality of sub-subjects to be screened from the ESG rating reports and subject scores corresponding to the sub-subjects to be screened respectively,
step S3, based on the plurality of sub-subjects to be screened and the subject scores, a plurality of common factors having influence on the ESG rating results are induced from the plurality of sub-subjects to be screened, contribution degrees corresponding to the common factors are obtained, the contribution degrees are used for representing the influence degree of the corresponding common factors on the ESG rating results, each common factor corresponds to part of the sub-subjects to be screened,
step S4, determining a target factor from the plurality of common factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of common factors,
step S5, determining the partial sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened,
step S6, determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic.
The content of steps S1 to S5 is identical to the content of the method for screening ESG subissues in the embodiment shown in fig. 1, and is not repeated here.
In this embodiment, after determining the target sub-issue, the ESG rating is performed by scoring the corresponding sub-issue, and after dimension reduction is performed on the sub-issue to be screened to obtain the target sub-issue, the user only needs to provide the data corresponding to the target sub-issue, so that convenience in performing the ESG rating by the user is improved.
Optionally, step S6, determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic, includes:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
The ESG rating report is rated according to the environment, society and corporate governance conditions of a certain company in a certain time period, and the share price and the income ratio of the company in the time period corresponding to the ESG rating report are obtained while the ESG rating report is obtained.
The determining of the rating weight of each sub-topic to be screened may be performed by using a weight model, which is specifically as follows: and acquiring a training data set, wherein the training data set comprises a plurality of ESG rating reports and corresponding stock price profitability, and the training data set has better training effect as the data volume is larger. And training the weight model by taking the topic score corresponding to the sub-topic to be screened selected in the ESG rating report as a characteristic value and the stock price yield as a target value and adopting an extreme gradient lifting tree (eXtreme Gradient Boosting, XGBoost) algorithm. After the parameter adjustment optimization and training are completed, the relative importance of each feature is output by using a feature_importances_function built in the XGBoost. There are 5 importance categories for the importance_type of XGBoost: weight, gain, cover, total _gain and total_cover. Optionally, gain represents the average information gain of all segmentations using the feature, the relative importance of gain correspondence being determined as the ranking weight of the sub-topics.
Based on the rating weight of each sub-topic to be screened, a rating weight of the target sub-topic is determined. When the ESG rating is carried out, the product of the rating weight of each target sub-topic and the topic score is obtained, and then the product of the rating weight of each target sub-topic and the topic score is summed to finally obtain an ESG rating result.
In this embodiment, a corresponding rating weight is obtained for each target sub-issue, and then the ESG rating result is determined by using the rating weight and the issue score of the target sub-issue, thereby improving the accuracy and objectivity of the ESG rating result.
The execution body of the method for screening an ESG sub-issue provided in the embodiment of the present application may be an ESG sub-issue screening device, taking the method for screening an ESG sub-issue executed by the ESG sub-issue screening device as an example, referring to fig. 3, the ESG sub-issue screening device 400 provided in the embodiment of the present application is described, where the ESG sub-issue screening device 400 includes:
a first obtaining module 401, configured to obtain a plurality of ESG rating reports;
a selecting module 402, configured to select a plurality of sub-topics to be screened from the plurality of ESG rating reports and topic scores corresponding to the plurality of sub-topics to be screened;
a second obtaining module 403, configured to sum up a plurality of commonality factors having an effect on the ESG rating result from the plurality of sub-topics to be screened based on the plurality of sub-topics to be screened and the topic score, and obtain contribution degrees corresponding to the plurality of commonality factors, where the contribution degrees are used to characterize the effect degree of the corresponding commonality factors on the ESG rating result, and each of the commonality factors corresponds to a part of sub-topics in the plurality of sub-topics to be screened;
a first determining module 404, configured to determine a target factor from the plurality of commonality factors based on a preset contribution threshold and a contribution corresponding to each of the plurality of commonality factors;
the second determining module 405 is configured to determine, from the sub-topics to be screened, a part of the sub-topics corresponding to the target factor as target sub-topics.
Optionally, in the case that the number of the target factors is a plurality of, a sum of contribution degrees corresponding to the target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
Optionally, the second determining module 405 is further configured to:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
Optionally, the screening apparatus 400 of the ESG sub-issue further includes a rating module, configured to determine an ESG rating result based on the target sub-issue and the issue score corresponding to the target sub-issue.
Optionally, the evaluation module is further configured to:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
The screening device 400 of the ESG sub-issue according to the embodiment of the present application may select a plurality of sub-issues to be screened and issue scores corresponding to each sub-issue to be screened from a plurality of ESG rating reports, sum up common factors and contribution degrees corresponding to the common factors according to the sub-issues to be screened and the issue scores, and determine a target sub-issue from the sub-issues to be screened according to a relationship between the contribution degrees corresponding to the common factors and a preset contribution degree.
It should be noted that, the screening device 400 for ESG sub-issues provided in the embodiment of the present application can implement all technical processes of the screening method for ESG sub-issues and achieve the same technical effects, and is not repeated here.
The device in the embodiment of the application can be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. By way of example, the electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a mobile internet appliance (Mobile Internet Device, MID), an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and the non-mobile electronic device may also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a Television (TV), a teller machine, a self-service machine, etc., without limitation in the embodiments of the present application.
Optionally, as shown in fig. 4, the embodiment of the present application further provides an electronic device 500, including a processor 501 and a memory 502, where the memory 502 stores a program or an instruction that can be executed on the processor 501, and the program or the instruction when executed by the processor 501 implements each step of the above-mentioned method embodiment for screening ESG sub-topics, and can achieve the same technical effects, so that repetition is avoided and no further description is given here.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.
The embodiment of the application also provides a readable storage medium, on which a program or an instruction is stored, which when executed by a processor, implements each process of the above-mentioned ESG sub-issue screening method embodiment, and can achieve the same technical effect, so that repetition is avoided, and no further description is given here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The foregoing is merely illustrative embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present application, and the application should be covered. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (12)
1. A screening method for governance of ESG sub-topics for environments, society and companies, the method comprising obtaining a plurality of ESG rating reports; selecting a plurality of sub-topics to be screened from the ESG rating reports and topic scores corresponding to the plurality of sub-topics to be screened respectively, wherein the method further comprises:
based on the plurality of sub-subjects to be screened and the subject scores, a plurality of common factors influencing the ESG rating results are induced from the plurality of sub-subjects to be screened, and contribution degrees corresponding to the common factors are obtained, wherein the contribution degrees are used for representing the influence degree of the corresponding common factors on the ESG rating results, and each common factor corresponds to part of the sub-subjects in the plurality of sub-subjects to be screened;
determining a target factor from the plurality of commonality factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of commonality factors;
and determining a part of sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened.
2. The method for screening ESG sub-topics of claim 1, wherein, if the number of target factors is plural, a sum of contribution degrees corresponding to the target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
3. The method for screening ESG sub-topics of claim 1, wherein determining a part of sub-topics corresponding to the target factor as a target sub-topic from the sub-topics to be screened includes:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
4. The method for screening ESG sub-topics according to any one of claims 1 to 3, wherein after determining a part of sub-topics corresponding to the target factor as a target sub-topic from the sub-topics to be screened, the method further comprises:
and determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic.
5. The method for screening ESG sub-topics of claim 4, wherein determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic comprises:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
6. A screening device for ESG sub-topics, wherein the device includes a first acquiring module and a selecting module, the first acquiring module is configured to acquire a plurality of ESG rating reports, the selecting module is configured to select a plurality of sub-topics to be screened and topic scores corresponding to the plurality of sub-topics to be screened from the plurality of ESG rating reports, and the device further includes:
the second obtaining module is configured to sum up a plurality of commonality factors having an influence on the ESG rating result from the plurality of sub-topics to be screened based on the plurality of sub-topics to be screened and the topic score, and obtain contribution degrees corresponding to the commonality factors, where the contribution degrees are used to characterize the influence degree of the corresponding commonality factors on the ESG rating result, and each of the commonality factors corresponds to a part of sub-topics in the plurality of sub-topics to be screened;
the first determining module is used for determining a target factor from the plurality of commonality factors based on a preset contribution threshold and the contribution corresponding to each of the plurality of commonality factors;
and the second determining module is used for determining a part of sub-topics corresponding to the target factors as target sub-topics from the sub-topics to be screened.
7. The ESG sub-topic screening apparatus of claim 6 wherein, if the number of target factors is plural, a sum of contribution degrees corresponding to the plural target factors is greater than or equal to the preset contribution degree threshold;
and under the condition that the number of the target factors is one, the contribution degree corresponding to the target factors is larger than or equal to the preset contribution degree threshold value.
8. The screening apparatus of the ESG sub-issue of claim 6, wherein the second determining module is further configured to:
determining a part of sub-subjects corresponding to the target factors from the sub-subjects to be screened as first sub-subjects, and acquiring importance corresponding to the first sub-subjects, wherein the importance is used for representing the influence degree of the first sub-subjects on the corresponding target factors;
determining the target sub-issue from the first sub-issue, wherein the importance corresponding to the target sub-issue is greater than or equal to a preset importance threshold.
9. The ESG sub-topic screening apparatus of any one of claims 6 to 8, further comprising a rating module for determining an ESG rating result based on the target sub-topic and topic scores corresponding to the target sub-topic.
10. The screening apparatus of ESG subtopics of claim 9, wherein the rating module is further configured to:
acquiring the share price profitability corresponding to each of the ESG rating reports;
determining a rating weight of each sub-topic to be screened based on the stock price yield and topic scores corresponding to the sub-topics to be screened;
determining the rating weight corresponding to the target sub-topic from the rating weight of each sub-topic to be screened;
and determining the ESG rating result based on the target sub-topic, the topic score corresponding to the target sub-topic and the rating weight corresponding to the target sub-topic.
11. An electronic device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the method of screening ESG sub-topics as claimed in any one of claims 1 to 5.
12. A readable storage medium, wherein a program or instructions is stored on the readable storage medium, which when executed by a processor, implements the steps of the method for screening ESG sub-topics of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310930970.0A CN116664016B (en) | 2023-07-27 | 2023-07-27 | Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310930970.0A CN116664016B (en) | 2023-07-27 | 2023-07-27 | Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116664016A true CN116664016A (en) | 2023-08-29 |
| CN116664016B CN116664016B (en) | 2023-09-26 |
Family
ID=87717407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310930970.0A Active CN116664016B (en) | 2023-07-27 | 2023-07-27 | Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116664016B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019144850A (en) * | 2018-02-21 | 2019-08-29 | 国立大学法人京都大学 | Evaluation device, evaluation method, and program |
| CN112101481A (en) * | 2020-10-14 | 2020-12-18 | 平安科技（深圳）有限公司 | Method, device and equipment for screening influence factors of target object and storage medium |
| CN113657809A (en) * | 2021-08-31 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Hospital portrait construction method, device, equipment and storage medium |
| CN114169686A (en) * | 2021-11-11 | 2022-03-11 | 上海华证指数信息服务有限公司 | ESG evaluation method for listed company |
| CN114239697A (en) * | 2021-11-26 | 2022-03-25 | 杭州海康威视数字技术股份有限公司 | Target object classification method and device, electronic equipment and storage medium |
| CN114897558A (en) * | 2022-05-09 | 2022-08-12 | 浙江工业大学 | Creative design system based on consumer group creativity |
| CN114943458A (en) * | 2022-06-01 | 2022-08-26 | 海南绿色发展科技集团有限公司 | Enterprise ESG (electronic service guide) rating method based on weight distribution model |
| CN115310900A (en) * | 2022-07-30 | 2022-11-08 | 东南大学 | Big data early warning system for integrity management of network freight platform |
| TWM637699U (en) * | 2022-10-21 | 2023-02-11 | 群益證券投資信託股份有限公司 | Enterprise Rating System |
| CN116070911A (en) * | 2023-02-14 | 2023-05-05 | 河海大学 | Regional flood disaster risk evaluation method based on fuzzy clustering factor |
| CN116402546A (en) * | 2023-01-12 | 2023-07-07 | 广州欢聚时代信息科技有限公司 | Store risk attribution method and device, equipment, medium and product thereof |
-
2023
- 2023-07-27 CN CN202310930970.0A patent/CN116664016B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019144850A (en) * | 2018-02-21 | 2019-08-29 | 国立大学法人京都大学 | Evaluation device, evaluation method, and program |
| CN112101481A (en) * | 2020-10-14 | 2020-12-18 | 平安科技（深圳）有限公司 | Method, device and equipment for screening influence factors of target object and storage medium |
| CN113657809A (en) * | 2021-08-31 | 2021-11-16 | 平安医疗健康管理股份有限公司 | Hospital portrait construction method, device, equipment and storage medium |
| CN114169686A (en) * | 2021-11-11 | 2022-03-11 | 上海华证指数信息服务有限公司 | ESG evaluation method for listed company |
| CN114239697A (en) * | 2021-11-26 | 2022-03-25 | 杭州海康威视数字技术股份有限公司 | Target object classification method and device, electronic equipment and storage medium |
| CN114897558A (en) * | 2022-05-09 | 2022-08-12 | 浙江工业大学 | Creative design system based on consumer group creativity |
| CN114943458A (en) * | 2022-06-01 | 2022-08-26 | 海南绿色发展科技集团有限公司 | Enterprise ESG (electronic service guide) rating method based on weight distribution model |
| CN115310900A (en) * | 2022-07-30 | 2022-11-08 | 东南大学 | Big data early warning system for integrity management of network freight platform |
| TWM637699U (en) * | 2022-10-21 | 2023-02-11 | 群益證券投資信託股份有限公司 | Enterprise Rating System |
| CN116402546A (en) * | 2023-01-12 | 2023-07-07 | 广州欢聚时代信息科技有限公司 | Store risk attribution method and device, equipment, medium and product thereof |
| CN116070911A (en) * | 2023-02-14 | 2023-05-05 | 河海大学 | Regional flood disaster risk evaluation method based on fuzzy clustering factor |
Non-Patent Citations (1)
| Title |
|---|
| 常育;: "基于模糊综合评价法的医疗机构药师综合绩效考评研究", 中国药房, no. 13 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116664016B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Engida et al. | Measuring corporate sustainability performance–the case of European food and beverage companies | |
| Ferrier et al. | A new predictor of the irreplaceability of areas for achieving a conservation goal, its application to real-world planning, and a research agenda for further refinement | |
| Currim et al. | A comparative evaluation of multiattribute consumer preference models | |
| Becker | Making sustainable development evaluations work | |
| Pontius Jr et al. | Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment | |
| Venkata Rao et al. | Decision making in the manufacturing environment using an improved PROMETHEE method | |
| Alkarkhi et al. | Easy statistics for food science with R | |
| US20070015125A1 (en) | Automated updating of job assessments | |
| US7761797B2 (en) | Interactive user interface for displaying correlation | |
| CN112016826A (en) | Method and device for determining corrosion degree of transformer substation equipment and computer equipment | |
| Çağrı Tolga et al. | Fuzzy multiattribute evaluation of R&D projects using a real options valuation model | |
| Burke et al. | Using and abusing QFD scores | |
| CN115203496A (en) | Project intelligent prediction and evaluation method and system based on big data and readable storage medium | |
| Ocampo | Fuzzy analytic network process (FANP) approach in formulating infrastructural decisions of sustainable manufacturing strategy | |
| US11295325B2 (en) | Benefit surrender prediction | |
| Costa et al. | Automatic classification of computational thinking skills in elementary school math questions | |
| Lee et al. | Comparing random effects models, ordinary least squares, or fixed effects with cluster robust standard errors for cross-classified data. | |
| CN116664016B (en) | Screening method and device of ESG (electronic service guide) sub-topics, electronic equipment and readable storage medium | |
| Owuor | Implications of using Likert data in multiple regression analysis | |
| Kabak et al. | A holistic evaluation of the e-procurement website by using a hybrid MCDM methodology | |
| Mat Roni et al. | Preliminary data analysis: An analysis before the analysis | |
| Feili et al. | Integration of fuzzy analytic hierarchy process (FAHP) with balance score card (BSC) in order to evaluate the performance of information technology in industry | |
| Sari et al. | The determination of website usability components by using generalized structured component analysis | |
| Jin* et al. | A new t-test for the R/S analysis and long memory in agricultural commodity prices | |
| CN111506826A (en) | User recommendation method, device, equipment and storage medium based on intimacy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |