Ryan Ferrera, John Mark Pittman, M. Zapryanov, Oliver Schaer, Stephen Adams
{"title":"零售商的困境:个性化产品营销以实现收益最大化","authors":"Ryan Ferrera, John Mark Pittman, M. Zapryanov, Oliver Schaer, Stephen Adams","doi":"10.1109/sieds49339.2020.9106672","DOIUrl":null,"url":null,"abstract":"Companies face many challenges when it comes to increasing revenue, but one of them is how to turn low or no-revenue customers into high revenue customers. When surveying their opportunities to do so, companies often turn to marketing. However, when deciding which among the many options to market to an existing customer, with only finite resources to do so, companies must make a choice rooted in the expected value that reflects the customer’s interest in the offer and the business value of that product or feature. This paper explores techniques to identify customers and study product allocations that allow to increase revenue by nudging customers from lower-revenue groups to higher-revenue groups by recommending the next product to market. Our approach utilizes k-means clustering to identify customer segments based on the recency, frequency, and monetary value (RFM) of their purchases. Further, we demonstrate that an association analysis technique called Market Basket Analysis (MBA) can be extended to not only identify products commonly purchased with the products a specific customer already has, but also to identify which products are associated with higher-revenue customer behavior. We close with a discussion on how these two techniques (clustering and association analysis) can be combined to optimally nudge customers from low-revenue groups to high-revenue groups by incrementally marketing products that more-closely align with the purchasing behavior of higher-revenue customers.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Retailer’s Dilemma: Personalized Product Marketing to Maximize Revenue\",\"authors\":\"Ryan Ferrera, John Mark Pittman, M. Zapryanov, Oliver Schaer, Stephen Adams\",\"doi\":\"10.1109/sieds49339.2020.9106672\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Companies face many challenges when it comes to increasing revenue, but one of them is how to turn low or no-revenue customers into high revenue customers. When surveying their opportunities to do so, companies often turn to marketing. However, when deciding which among the many options to market to an existing customer, with only finite resources to do so, companies must make a choice rooted in the expected value that reflects the customer’s interest in the offer and the business value of that product or feature. This paper explores techniques to identify customers and study product allocations that allow to increase revenue by nudging customers from lower-revenue groups to higher-revenue groups by recommending the next product to market. Our approach utilizes k-means clustering to identify customer segments based on the recency, frequency, and monetary value (RFM) of their purchases. Further, we demonstrate that an association analysis technique called Market Basket Analysis (MBA) can be extended to not only identify products commonly purchased with the products a specific customer already has, but also to identify which products are associated with higher-revenue customer behavior. We close with a discussion on how these two techniques (clustering and association analysis) can be combined to optimally nudge customers from low-revenue groups to high-revenue groups by incrementally marketing products that more-closely align with the purchasing behavior of higher-revenue customers.\",\"PeriodicalId\":331495,\"journal\":{\"name\":\"2020 Systems and Information Engineering Design Symposium (SIEDS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Systems and Information Engineering Design Symposium (SIEDS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/sieds49339.2020.9106672\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Systems and Information Engineering Design Symposium (SIEDS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/sieds49339.2020.9106672","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Retailer’s Dilemma: Personalized Product Marketing to Maximize Revenue
Companies face many challenges when it comes to increasing revenue, but one of them is how to turn low or no-revenue customers into high revenue customers. When surveying their opportunities to do so, companies often turn to marketing. However, when deciding which among the many options to market to an existing customer, with only finite resources to do so, companies must make a choice rooted in the expected value that reflects the customer’s interest in the offer and the business value of that product or feature. This paper explores techniques to identify customers and study product allocations that allow to increase revenue by nudging customers from lower-revenue groups to higher-revenue groups by recommending the next product to market. Our approach utilizes k-means clustering to identify customer segments based on the recency, frequency, and monetary value (RFM) of their purchases. Further, we demonstrate that an association analysis technique called Market Basket Analysis (MBA) can be extended to not only identify products commonly purchased with the products a specific customer already has, but also to identify which products are associated with higher-revenue customer behavior. We close with a discussion on how these two techniques (clustering and association analysis) can be combined to optimally nudge customers from low-revenue groups to high-revenue groups by incrementally marketing products that more-closely align with the purchasing behavior of higher-revenue customers.