نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه قم، قم، ایران
2 گروه فناوری اطلاعات ، دانشکده فناوری اطلاعات و مهندسی کامپیوتر، دانشگاه شهید مدنی آذربایجان، تبریز، ایران
3 عضو هیات علمی گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه قم، قم، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Purpose: The objective of this study is to analyze customer behavior using multivariate time series data. After a detailed analysis and understanding of customers, their prioritization is carried out using the TOPSIS multi-criteria decision-making method. The results of this study can assist organizations in developing marketing strategies.
Method: In this research, the approach of analyzing customers' dynamic behavior using RFM (recency, frequency, monetary value) variables in the form of multivariable time series, which is one of the most recent and most practical methods of analyzing customers' behavior over time, has been used. Then, using an ensemble time series clustering method, the customers' clusters were identified, and their behavioral patterns were analyzed from different perspectives. After this step, key features were extracted from each time series and considered as the input of a classification model. Finally, by employing Shapley additive explanations (SHAP), the classifier model is interpreted, and the importance of each of the key features is calculated. The key features, along with their weights, are used in the TOPSIS multi-criteria decision-making method in order to prioritize customers.
Findings: The findings of this research show that by representing customer purchase data in the form of a multivariate time series consisting of RFM variables, it is possible to identify similar groups of customers with similar behavior patterns over time. The proposed approach simultaneously considers RFM variables over time and analyzes the dynamic behavior of customers. Also, the application of the SHAP method in calculating the importance of critical features of customer behavior was shown in this research. Then, using the TOPSIS multi-criteria decision-making method, customers were ranked based on importance and priority in the marketing strategy. These results can help the organization in formulating targeted and effective marketing strategies.
Conclusion: The results show that the proposed approach of the research provides the possibility to identify the behavioral patterns of customers. These analyses assist the organization in identifying the behavioral patterns of customers more effectively and targeting valuable customers in the marketing strategy according to prioritization. In general, the results of this research support organizations to formulate an effective marketing strategy and increase their marketing efficiency by recognizing and analyzing customers' behavior patterns.
Purpose: The objective of this study is to analyze customer behavior using multivariate time series data. After a detailed analysis and understanding of customers, their prioritization is carried out using the TOPSIS multi-criteria decision-making method. The results of this study can assist organizations in developing marketing strategies.
Method: In this research, the approach of analyzing customers' dynamic behavior using RFM (recency, frequency, monetary value) variables in the form of multivariable time series, which is one of the most recent and most practical methods of analyzing customers' behavior over time, has been used. Then, using an ensemble time series clustering method, the customers' clusters were identified, and their behavioral patterns were analyzed from different perspectives. After this step, key features were extracted from each time series and considered as the input of a classification model. Finally, by employing Shapley additive explanations (SHAP), the classifier model is interpreted, and the importance of each of the key features is calculated. The key features, along with their weights, are used in the TOPSIS multi-criteria decision-making method in order to prioritize customers.
Findings: The findings of this research show that by representing customer purchase data in the form of a multivariate time series consisting of RFM variables, it is possible to identify similar groups of customers with similar behavior patterns over time. The proposed approach simultaneously considers RFM variables over time and analyzes the dynamic behavior of customers. Also, the application of the SHAP method in calculating the importance of critical features of customer behavior was shown in this research. Then, using the TOPSIS multi-criteria decision-making method, customers were ranked based on importance and priority in the marketing strategy. These results can help the organization in formulating targeted and effective marketing strategies.
Conclusion: The results show that the proposed approach of the research provides the possibility to identify the behavioral patterns of customers. These analyses assist the organization in identifying the behavioral patterns of customers more effectively and targeting valuable customers in the marketing strategy according to prioritization. In general, the results of this research support organizations to formulate an effective marketing strategy and increase their marketing efficiency by recognizing and analyzing customers' behavior patterns.
کلیدواژهها [English]
ارسال نظر در مورد این مقاله