Prediction method and system for green purchase behavior of consumer
By constructing multi-theoretical models and PLS-SEM analysis, identifying and verifying factors that affect consumers' green purchasing behavior, the problem of lack of systematic verification in existing research is solved, and scientific prediction and accurate prediction of green purchasing behavior are achieved.
Patent Information
- Application Number
- CN202411232285.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-12-27
AI Technical Summary
Existing research is difficult to systematically explore and verify factors that affect consumers' green purchasing behavior, and lacks scientific and effective methods to formulate theoretical models and provide practical guidance.
Construct a consumption behavior theory model based on planned behavior theory, value-belief-normative theory, social dilemma theory and clue utilization theory, analyze sample data using the PLS-SEM model, identify the influence mechanism of green purchasing behavior and make predictions.
Through quantitative analysis and path coefficient verification, the accuracy and reliability of prediction methods are improved, providing scientific basis for enterprises and policy makers to quickly identify key factors and future trends that affect green purchasing behavior.
Smart Images
Figure CN119205191A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of consumer behavior prediction, and in particular relates to a method and system for predicting consumer green purchasing behavior. Background Art
[0002] As global awareness of environmental protection increases, green consumption has gradually become a hot topic of social concern. However, the factors that affect consumers' green purchasing behavior are complex and diverse, and the interaction mechanism between these factors is still unclear. Existing studies mostly use questionnaire surveys and theoretical models (such as the theory of planned behavior TPB, the value-belief-norm theory VBN, etc.) to explore the influencing factors of green purchasing behavior, but these studies mainly stay at the level of theoretical analysis and data interpretation, lacking a direct conversion of research results into highly operational technical solutions.
[0003] Therefore, although some studies have attempted to explore the influencing factors of green purchasing behavior, most of them use single variable analysis or qualitative research methods, lacking systematic theoretical model support and quantitative verification. How to develop a scientific and effective method to systematically derive the influencing mechanism of green purchasing behavior and provide theoretical basis and practical guidance for policy makers, enterprises and consumers is an urgent problem that technical personnel in this field need to solve. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for predicting consumers' green purchasing behavior to solve the problems raised in the background technology.
[0005] The present invention achieves the above-mentioned purpose through the following technical solutions:
[0006] In a first aspect, the present invention proposes a method for predicting consumer green purchasing behavior, the method comprising:
[0007] Collect a sample data set of consumers’ opinions on factors that influence green purchasing behavior;
[0008] Based on the theory of planned behavior, value-belief-norm theory, social dilemma theory and cue utilization theory, a consumer behavior theoretical model was constructed. Product-related factors, consumer psychological factors and environmental influencing factors were selected as antecedent variables, and green purchasing behavior was used as the dependent variable. Several connection trajectories between antecedent variables and dependent variables were defined and drawn to form the influencing mechanism of green purchasing behavior.
[0009] Constructing a PLS-SEM model and analyzing the sample data set, connecting the variables in the sample data set in the PLS-SEM model according to the plurality of connection trajectories, performing model fitting and verification, and outputting the analysis results of the PLS-SEM model;
[0010] Consumers' green purchasing behavior is predicted based on the analysis results and the influencing mechanism.
[0011] Furthermore, the sample data set includes the following variables: perceived effectiveness, climate change risk perception, eco-label, perceived high price, environmental knowledge, policy incentives, perceived low quality, green advertising skepticism, subjective norms, awareness of consequences, personal norms, green purchasing attitude, perceived behavioral control, green purchasing intention, and green purchasing behavior.
[0012] Furthermore, among the antecedent variables, the product-related factors include: perceived high price, perceived low quality, eco-label and green advertising suspicion; the consumer psychological factors include climate change risk perception and perceived effectiveness; and the environmental influencing factors include environmental knowledge.
[0013] Furthermore, the constructing of the PLS-SEM model and analyzing the sample data set include: performing reliability and validity tests on the PLS-SEM model based on the sample data set, specifically including reliability analysis, structural validity analysis, convergent validity analysis and discriminant validity analysis.
[0014] Furthermore, the variables in the sample data set are connected in the PLS-SEM model according to the connection trajectories, and after the model is fitted and verified, the analysis results of the PLS-SEM model are output, including:
[0015] Hypothesis test: taking several connection trajectories as hypotheses, connecting the variables in the sample data set in the PLS-SEM model according to the several connection trajectories, and then performing significance tests on the several connection trajectories in combination with the Bootstrap test, and determining whether the hypothesis is established based on the significance results;
[0016] Model fitting: The model fitting effect was judged according to the SRMR value output by the PLS-SEM model;
[0017] Model validation: R based on the output of the PLS-SEM model 2 The value determines the explanatory power of each variable in the sample data set on green purchasing behavior.
[0018] Furthermore, the predicting of consumer green purchasing behavior based on the analysis results and the influencing mechanism includes: 2 The values of green purchasing behavior are determined by the key influencing variables.
[0019] In a second aspect, the present invention proposes a consumer green purchasing behavior prediction system, which is applied to execute any of the above prediction methods, and the system comprises:
[0020] The data collection module is used to collect sample data sets of consumers’ information on factors that influence green purchasing behavior;
[0021] Model building module, which is used to build a consumer behavior theory model based on the theory of planned behavior, value-belief-norm theory, social dilemma theory and cue utilization theory, select product-related factors, consumer psychological factors and environmental influencing factors as antecedent variables, take green purchasing behavior as the dependent variable, define and draw several connection trajectories between antecedent variables and dependent variables, so as to form the influencing mechanism of green purchasing behavior;
[0022] A data analysis module is used to construct a PLS-SEM model and analyze the sample data set, connect the variables in the sample data set in the PLS-SEM model according to the plurality of connection trajectories, perform model fitting and verification, and output the analysis results of the PLS-SEM model;
[0023] A prediction module is used to predict the consumer's green purchasing behavior based on the analysis results and the influencing mechanism.
[0024] The beneficial effects of the present invention are:
[0025] 1. The prediction method in the present invention can quickly identify the key factors affecting green purchasing behavior based on large-scale consumer data, and predict future consumption trends, providing a scientific basis for enterprises to formulate effective green marketing strategies.
[0026] 2. This paper constructs a theoretical model to comprehensively sort out the various factors that affect green purchasing behavior and their interrelationships, providing a systematic framework for in-depth research, and uses the PLS-SEM model to quantitatively analyze the collected data. Through path coefficients and significance tests, the validity of each hypothesis is scientifically verified, thereby improving the accuracy and reliability of the prediction method. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 A flowchart of a method for predicting consumer green purchasing behavior provided in an embodiment of the present application.
[0028] Figure 2 This is a diagram of the architecture of the consumer behavior theoretical model in the method for predicting consumer green purchasing behavior provided in an embodiment of the present application. DETAILED DESCRIPTION
[0029] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.
[0030] Example 1
[0031] like Figure 1-2 As shown, this embodiment proposes a method for predicting consumer green purchasing behavior, and the method includes the following steps:
[0032] S1. Collect a sample data set of consumers’ information on factors that influence green purchasing behavior; the sample data set includes the following variables: perceived effectiveness, climate change risk perception, eco-label, perceived high price, environmental knowledge, policy incentives, perceived low quality, green advertising skepticism, subjective norms, awareness of consequences, personal norms, green purchasing attitude, perceived behavioral control, green purchasing intention, and green purchasing behavior.
[0033] S2. Based on the theory of planned behavior (TPB), value-belief-norm theory (VBN), social dilemma theory and cue utilization theory, a consumer behavior theoretical model was constructed. Product-related factors, consumer psychological factors and environmental influencing factors were selected as antecedent variables, and green purchasing behavior was taken as the dependent variable. Several connection trajectories between antecedent variables and dependent variables were defined and drawn to form the influencing mechanism of green purchasing behavior.
[0034] Among the antecedent variables, product-related factors include: perceived high price, perceived low quality, eco-labeling and suspicion of green advertising; consumer psychological factors include climate change risk perception and perceived effectiveness; and environmental influencing factors include environmental knowledge.
[0035] S3. Construct a PLS-SEM model (variance-based partial least squares structural equation model) and analyze the sample data set. Connect the variables in the sample data set in the PLS-SEM model according to several connection trajectories. After performing model fitting and verification, output the analysis results of the PLS-SEM model.
[0036] S4. Predict consumers’ green purchasing behavior based on the analysis results and influencing mechanisms.
[0037] It can be understood that this embodiment proposes to integrate multiple behavioral theories (TPB theory, VBN theory, cue utilization theory and social dilemma theory) to construct a consumer behavior theoretical model and explore the impact mechanism of relevant variables on green purchasing behavior.
[0038] Further preferably, constructing a PLS-SEM model and analyzing the sample data set includes: performing reliability and validity tests on the PLS-SEM model based on the sample data set, specifically including reliability analysis, structural validity analysis, convergent validity analysis and discriminant validity analysis.
[0039] First of all, structural validity analysis refers to the extent to which a detection tool can truly measure the expected theoretical structure, that is, whether the items contained in the evaluation scale are consistent with the measurement dimension. Generally, the factor loading coefficient is used to measure structural validity. The factor loading coefficient represents the contribution of the corresponding item to a certain dimension. The larger the factor loading coefficient, the greater the connection between the item and the corresponding dimension. Convergent validity refers to the extent to which items measuring the same latent variable converge to the same factor. Generally, the average variance extraction AVE value and the combined reliability CR value are used as test indicators of convergent validity. Discriminant validity refers to the extent to which differences between different latent variables in the model can be effectively distinguished. This embodiment uses the Fornell-Larcker standard to determine the discriminant validity, that is, when the AVE square root value of the latent variable is greater than the correlation coefficient between the latent variable and other latent variables, it indicates good discriminant validity.
[0040] Secondly, reliability refers to the degree to which the results can remain consistent when the same measurement tool is used to repeatedly measure the same object. Cronbach's α value is generally used as a test indicator.
[0041] Further preferably, each variable in the sample data set is connected in the PLS-SEM model according to a number of connection trajectories, and after performing model fitting and verification, the analysis results of the PLS-SEM model are output, including:
[0042] Hypothesis Testing: Combining Figure 2 , taking several connection trajectories as hypotheses, connecting the variables in the sample data set according to several connection trajectories in the PLS-SEM model, and then combining the Bootstrap test to perform significance tests on several connection trajectories, and determining whether the hypothesis is established based on the significance results;
[0043] Model fitting: The model fitting effect was judged according to the SRMR value output by the PLS-SEM model;
[0044] Model validation: R based on the output of the PLS-SEM model 2 The value determines the explanatory power of each variable in the sample data set on green purchasing behavior.
[0045] Further preferably, the consumer green purchasing behavior is predicted based on the analysis results and the influencing mechanism, including: based on the hypothesis test results and R 2 The values of green purchasing behavior are determined by the key influencing variables.
[0046] Based on the same inventive concept, this embodiment also proposes a consumer green purchasing behavior prediction system, which is applied to execute the above prediction method. The system includes:
[0047] The data collection module is used to collect sample data sets of consumers’ information on factors that influence green purchasing behavior;
[0048] Model building module, which is used to build a consumer behavior theory model based on the theory of planned behavior, value-belief-norm theory, social dilemma theory and cue utilization theory, select product-related factors, consumer psychological factors and environmental influencing factors as antecedent variables, take green purchasing behavior as the dependent variable, define and draw several connection trajectories between antecedent variables and dependent variables, so as to form the influencing mechanism of green purchasing behavior;
[0049] The data analysis module is used to construct a PLS-SEM model and analyze the sample data set, connect the variables in the sample data set in the PLS-SEM model according to several connection trajectories, perform model fitting and verification, and output the analysis results of the PLS-SEM model;
[0050] The prediction module is used to predict consumers' green purchasing behavior based on the analysis results and influencing mechanisms.
[0051] It should be noted here that each module in the above prediction system corresponds to steps S1 to S4 in implementing the above prediction method, and the instances and application scenarios implemented by multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment 1.
[0052] The above prediction method is further described in detail below in conjunction with a specific implementation program.
[0053] 1. The sample data set is obtained by questionnaire survey:
[0054] The questionnaire in this example contains a total of 47 items. In order to ensure the effectiveness of the questionnaire survey, 10 consumers were selected for a pre-survey before the formal survey. According to the feedback from the surveyors, the sentences of some questions were modified without changing the original meaning of the items to ensure that the subsequent surveyors understand the meaning of the questionnaire questions. The questionnaire adopts a Likert 7-level scale structure, "1" represents strongly disagree, and "7" represents strongly agree, allowing the surveyors to make choices based on their actual situation. The questionnaire contains two parts. The first part counts the demographic variable information of the respondents, including age, education level, city of residence and monthly income. The second part of the questionnaire involves 15 variables included in the model. The items included in the questionnaire designed in this example and the sources of the items are shown in Table 1.
[0055] Table 1 Questionnaire measurement topics and sources
[0056]
[0057]
[0058] 2. Sample characteristics:
[0059] This example distributes questionnaires to consumers nationwide to obtain more extensive survey information. Questionnaire data was collected online through the Wenjuxing and Wenjuwang platforms from July 25, 2023 to September 5, 2023. The surveyed populations covered 31 provinces, municipalities, and autonomous regions in China. A total of 1,205 questionnaire data were collected in this example. First, the questionnaire data with a filling time of less than 2 minutes were deleted, because the filling time was too short and the filler was likely not to have carefully thought about the questionnaire items, so the filling results were unreliable; secondly, the invalid questionnaires with obvious errors in the questionnaire filling logic were deleted, and finally 877 valid questionnaires remained, with an effective recovery rate of 72.78%.
[0060] 3. Data analysis methods:
[0061] This example uses the structural equation model to analyze the questionnaire data. The structural equation model is a model method for establishing, estimating and testing the causal relationship between variables, including measurement relationship and influence relationship. The structural equation model can measure the internal structure of factors and their correlation, and can also measure the influence relationship between multiple independent variables and dependent variables at the same time. This example selects PLS-SEM for empirical testing. This example first uses SmartPLS 4.0.9.5 software to test the measurement model, including reliability analysis and structural validity analysis, convergent validity analysis, and discriminant validity analysis, and then tests the structural model again to verify whether the hypothesis is valid.
[0062] 4. Reliability and validity test:
[0063] 4.1. Validity test:
[0064] As shown in Table 2, the factor standard loading coefficients of all scale items are greater than the threshold of 0.5, indicating that each scale has good structural validity. As shown in Table 2, the AVE values of all scales are greater than 0.5, and the CR values are greater than 0.7, indicating that the scales used in this example have good convergent validity. This example uses the Fornell-Larcker standard to determine discriminant validity, that is, when the AVE square root value of the latent variable is greater than the correlation coefficient between the latent variable and other latent variables, it indicates good discriminant validity. As shown in Table 3, all scales used in this example have good discriminant validity.
[0065] 4.2 Reliability test:
[0066] Reliability refers to the degree to which the results can remain consistent when the same measurement tool is used to repeatedly measure the same object. Cronbach's α value is generally used as a test indicator. As shown in Table 2, the Cronbach's α value of each scale is greater than 0.7, indicating that the reliability of the scale used in this example is good.
[0067] Table 2 Reliability and convergent validity test
[0068]
[0069]
[0070] Table 3 Discriminant validity test
[0071]
[0072]
[0073] Note: The diagonal line is the value of the square root of AVE.
[0074] 5. Hypothesis test results
[0075] Based on PLS-SEM modeling, the Bootstrap test method was used to test whether the hypothesis was established by sampling the data multiple times. The SRMR value of the structural equation model was 0.090, which was less than 0.1, indicating that the model had a good fitting effect. In addition, R 2 The value is also an important indicator for evaluating the model fitting effect. It can evaluate the degree of explanation of the model, that is, the degree of fit of the model to the outcome variable. 2 The closer the value is to 1, the better the model’s explanation. 2 The values are all greater than 0. Among them, the explanatory power of the structural equation model for green purchasing behavior is 78.7%, the explanatory power for green purchasing intention is 72.8%, the explanatory power for green purchasing attitude is 66.7%, the explanatory power for personal norms is 59.5%, and the explanatory power for consequence awareness is 62.2%. Therefore, it shows that the model has a good explanatory effect on the dependent variables.
[0076] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0077] In addition, each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0078] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0079] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for predicting consumer green purchasing behavior, characterized in that: The method comprises: Collect a sample data set of consumers’ opinions on factors that influence green purchasing behavior; Based on the theory of planned behavior, value-belief-norm theory, social dilemma theory and cue utilization theory, a consumer behavior theoretical model was constructed. Product-related factors, consumer psychological factors and environmental influencing factors were selected as antecedent variables, and green purchasing behavior was used as the dependent variable. Several connection trajectories between antecedent variables and dependent variables were defined and drawn to form the influencing mechanism of green purchasing behavior. Constructing a PLS-SEM model and analyzing the sample data set, connecting the variables in the sample data set in the PLS-SEM model according to the plurality of connection trajectories, performing model fitting and verification, and outputting the analysis results of the PLS-SEM model; Consumers' green purchasing behavior is predicted based on the analysis results and the influencing mechanism.
2. The method for predicting consumer green purchasing behavior according to claim 1, characterized in that: The sample data set includes the following variables: perceived effectiveness, climate change risk perception, eco-label, perceived high price, environmental knowledge, policy incentives, perceived low quality, green advertising skepticism, subjective norms, awareness of consequences, personal norms, green purchasing attitude, perceived behavioral control, green purchasing intention, and green purchasing behavior.
3. The method for predicting consumer green purchasing behavior according to claim 2, characterized in that: Among the antecedent variables, the product-related factors include: perceived high price, perceived low quality, eco-label and suspicion of green advertising; the consumer psychological factors include climate change risk perception and perceived effectiveness; and the environmental influencing factors include environmental knowledge.
4. The method for predicting consumer green purchasing behavior according to claim 1, characterized in that: The constructing of the PLS-SEM model and analyzing the sample data set include: performing reliability and validity tests on the PLS-SEM model based on the sample data set, specifically including reliability analysis, structural validity analysis, convergent validity analysis and discriminant validity analysis.
5. The method for predicting consumer green purchasing behavior according to claim 1, characterized in that: The variables in the sample data set are connected in the PLS-SEM model according to the connection trajectories, and after the model is fitted and verified, the analysis results of the PLS-SEM model are output, including: Hypothesis test: taking several connection trajectories as hypotheses, connecting the variables in the sample data set in the PLS-SEM model according to the several connection trajectories, and then performing significance tests on the several connection trajectories in combination with the Bootstrap test, and determining whether the hypothesis is established based on the significance results; Model fitting: The model fitting effect was judged according to the SRMR value output by the PLS-SEM model; Model validation: R based on the output of the PLS-SEM model 2 The value determines the explanatory power of each variable in the sample data set on green purchasing behavior.
6. A method for predicting consumer green purchasing behavior according to claim 5, characterized in that: The predicting of the consumer's green purchasing behavior according to the analysis results and the influencing mechanism includes: based on the hypothesis test results and the R 2 The values of green purchasing behavior are determined by the key influencing variables.
7. A consumer green purchasing behavior prediction system, characterized in that: Applied to executing the prediction method according to any one of claims 1 to 6, the system comprises: The data collection module is used to collect sample data sets of consumers’ information on factors that influence green purchasing behavior; Model building module, which is used to build a consumer behavior theory model based on the theory of planned behavior, value-belief-norm theory, social dilemma theory and cue utilization theory, select product-related factors, consumer psychological factors and environmental influencing factors as antecedent variables, take green purchasing behavior as the dependent variable, define and draw several connection trajectories between antecedent variables and dependent variables, so as to form the influencing mechanism of green purchasing behavior; A data analysis module is used to construct a PLS-SEM model and analyze the sample data set, connect the variables in the sample data set in the PLS-SEM model according to the plurality of connection trajectories, perform model fitting and verification, and output the analysis results of the PLS-SEM model; A prediction module is used to predict the consumer's green purchasing behavior based on the analysis results and the influencing mechanism.