마케팅 프로모션에 대한 세분화된 고객집단의 반응예측과 분리데이터 학습기반의 구매액 예측 (The) prediction of responds and purchase amounts of customers in marketing promotion using segmented customers and separated learning method원문보기
With the rapid growth of information technology, the field of data mining has empowered managers who are charge of the tasks in their company to present personalized and differentiated marketing programs to their customers. A number of competitive data mining techniques such as neural networks, SVMs...
With the rapid growth of information technology, the field of data mining has empowered managers who are charge of the tasks in their company to present personalized and differentiated marketing programs to their customers. A number of competitive data mining techniques such as neural networks, SVMs (Support Vector Machines), decision tree, logit, and genetic algorithms have been applied to predict customer response to marketing promotion. Most studies on customer response have focused on predicting whether they would respond to marketing promotion but have not considered customer characteristics. This paper aimed to predict segmented customer response to marketing promotion. We focused on dividing customers into segments, whereas most studies have predicted overall customer response. We deployed logistic regression, neural networks, and support vector machines to predict customer response that is a kind of dichotomous classification while the integrated approach was utilized to improve the performance of the predicted model. To segment customers, we utilized a SOM (Self-organizing Map) with quantitative measures such as recency, frequency, and monetary. The measures examine how recently customers have purchased, how often they purchase, and how much they spend respectively. We proposed an approach that could understand segmented customers and prioritize marketing promotion. Additionally, we employed SVR (Support Vector Regression) to forecast the purchase amount of customers for each customer rating. We classified customers from under five ratings on the basis of the purchase amount after executing a marketing promotion. The model proposed by us forecasted the purchase amount of customers in the same rating, and the marketing managers could make a differentiated and personalized marketing program for each customer even though they belonged to the same rating. In addition, we proposed a more efficient learning method by separating the learning samples. We employed two learning methods to compare the performance of the proposed learning method with that of the general learning method for SVRs. LMW (Learning Method using Whole data for purchasing customers) is a general learning method to forecast the purchase amount of customers, and LMS (Learning Method using Separated data to classify purchasing customers) is the proposed method, which creates four different SVR models for each class of customers. To evaluate the performance of models, we calculated MAE (Mean Absolute Error) and MAPE (Mean Absolute Percent Error) for each model to predict the purchase amount of customers. The model proposed by us was more accurate in forecasting the purchase amount of customers in each class. In addition, our approach will be useful for marketing managers when they need to select customers for their promotion. Even if customers belong to the same class, marketing managers can offer them a differentiated and personalized marketing promotion.
With the rapid growth of information technology, the field of data mining has empowered managers who are charge of the tasks in their company to present personalized and differentiated marketing programs to their customers. A number of competitive data mining techniques such as neural networks, SVMs (Support Vector Machines), decision tree, logit, and genetic algorithms have been applied to predict customer response to marketing promotion. Most studies on customer response have focused on predicting whether they would respond to marketing promotion but have not considered customer characteristics. This paper aimed to predict segmented customer response to marketing promotion. We focused on dividing customers into segments, whereas most studies have predicted overall customer response. We deployed logistic regression, neural networks, and support vector machines to predict customer response that is a kind of dichotomous classification while the integrated approach was utilized to improve the performance of the predicted model. To segment customers, we utilized a SOM (Self-organizing Map) with quantitative measures such as recency, frequency, and monetary. The measures examine how recently customers have purchased, how often they purchase, and how much they spend respectively. We proposed an approach that could understand segmented customers and prioritize marketing promotion. Additionally, we employed SVR (Support Vector Regression) to forecast the purchase amount of customers for each customer rating. We classified customers from under five ratings on the basis of the purchase amount after executing a marketing promotion. The model proposed by us forecasted the purchase amount of customers in the same rating, and the marketing managers could make a differentiated and personalized marketing program for each customer even though they belonged to the same rating. In addition, we proposed a more efficient learning method by separating the learning samples. We employed two learning methods to compare the performance of the proposed learning method with that of the general learning method for SVRs. LMW (Learning Method using Whole data for purchasing customers) is a general learning method to forecast the purchase amount of customers, and LMS (Learning Method using Separated data to classify purchasing customers) is the proposed method, which creates four different SVR models for each class of customers. To evaluate the performance of models, we calculated MAE (Mean Absolute Error) and MAPE (Mean Absolute Percent Error) for each model to predict the purchase amount of customers. The model proposed by us was more accurate in forecasting the purchase amount of customers in each class. In addition, our approach will be useful for marketing managers when they need to select customers for their promotion. Even if customers belong to the same class, marketing managers can offer them a differentiated and personalized marketing promotion.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.