TY - JOUR
T1 - Predicting interpurchase time in a retail environment using customer-product networks
T2 - An empirical study and evaluation
AU - Lismont, Jasmien
AU - Ram, Sudha
AU - Vanthienen, Jan
AU - Lemahieu, Wilfried
AU - Baesens, Bart
N1 - Publisher Copyright:
© 2018 Elsevier Ltd
PY - 2018/8/15
Y1 - 2018/8/15
N2 - In predictive analytics and statistics, entities are frequently treated as individual actors. However, in reality this assumption is not valid. In the context of retail, similar customers will behave and thus also purchase similarly to each other. By combining their behavior in an intelligent way, based on transaction history, we can leverage these connections and improve our ability to predict purchase outcomes. As such, we can create customer-product networks from which we can deduce information on customers expressing similar purchasing behavior. This allows us to exploit their preferences and predict which products are going to be sold significantly less often. We want to use this information mainly for gaining novel marketing insights on products. For example, if customers refrain from buying products this might be due to contextual reasons such as new complements or supplements, or new nearby shops. By using these networks on data from an offline European retail corporation, we are able to boost performance of the predictive models by 6% and the identification of these specific products by 20%. This indicates that the development of customer-product graphs in retail can lead to improved marketing intelligence. To our knowledge, this is one of the first studies to use customer-product networks for predictive modeling in an offline retail setting. Furthermore, we suggest an extensive set of product and network features which can guide future researchers and practitioners in their model development.
AB - In predictive analytics and statistics, entities are frequently treated as individual actors. However, in reality this assumption is not valid. In the context of retail, similar customers will behave and thus also purchase similarly to each other. By combining their behavior in an intelligent way, based on transaction history, we can leverage these connections and improve our ability to predict purchase outcomes. As such, we can create customer-product networks from which we can deduce information on customers expressing similar purchasing behavior. This allows us to exploit their preferences and predict which products are going to be sold significantly less often. We want to use this information mainly for gaining novel marketing insights on products. For example, if customers refrain from buying products this might be due to contextual reasons such as new complements or supplements, or new nearby shops. By using these networks on data from an offline European retail corporation, we are able to boost performance of the predictive models by 6% and the identification of these specific products by 20%. This indicates that the development of customer-product graphs in retail can lead to improved marketing intelligence. To our knowledge, this is one of the first studies to use customer-product networks for predictive modeling in an offline retail setting. Furthermore, we suggest an extensive set of product and network features which can guide future researchers and practitioners in their model development.
KW - Customer-product graph
KW - Interpurchase time
KW - Offline retail
KW - Purchase behavior
KW - Social network analytics
KW - Transactional data
UR - http://www.scopus.com/inward/record.url?scp=85044140749&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044140749&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2018.03.016
DO - 10.1016/j.eswa.2018.03.016
M3 - Article
AN - SCOPUS:85044140749
SN - 0957-4174
VL - 104
SP - 22
EP - 32
JO - Expert Systems with Applications
JF - Expert Systems with Applications
ER -