Predicting customer profitability during acquisition: Finding the optimal combination of data source and data mining technique

• Published in: Expert systems with applications Vol. 40; no. 6; pp. 2007 - 2012
• Main Authors: D’Haen, Jeroen, Van den Poel, Dirk, Thorleuchter, Dirk
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.05.2013; Elsevier
• Subjects: Accuracy; Added value; Applied sciences; B2B; Bagging; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Customer acquisition; Data mining; Data processing. List processing. Character string processing; Data source; Decision theory. Utility theory; Decision trees; Exact sciences and technology; Expert systems; External commercial data; Firm modelling; Marketing analytics; Mathematical models; Memory organisation. Data processing; Operational research and scientific management; Operational research. Management science; Optimization; Predictive analytics; Profitability; Software; Web crawling; Web mining; Customer acquisition; Marketing analytics; B2B; Web crawling; Profitability; Web mining; External commercial data; Predictive analytics; Data source; Bagging; Data type; Information extraction; Data mining; Decision tree; Modeling; Marketing; Aggregate model; Acquisition process; Sales; Classification; World wide web; Extended enterprise; Data analysis; Statistical analysis; Probabilistic approach; Data processing; Business to business; Information browsing; Internet; Added value
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.10.023

► Focus is on supporting the customer acquisition process with profitability modeling. ► Commercially-available data is augmented by web data. ► Combining both web data and commercial data leads to the best predictive results for lead qualification. The customer acquisition process is generally a stressful undertaking for sales representatives. Luckily there are models that assist them in selecting the ‘right’ leads to pursue. Two factors play a role in this process: the probability of converting into a customer and the profitability once the lead is in fact a customer. This paper focuses on the latter. It makes two main contributions to the existing literature. Firstly, it investigates the predictive performance of two types of data: web data and commercially available data. The aim is to find out which of these two have the highest accuracy as input predictor for profitability and to research if they improve accuracy even more when combined. Secondly, the predictive performance of different data mining techniques is investigated. Results show that bagged decision trees are consistently higher in accuracy. Web data is better in predicting profitability than commercial data, but combining both is even better. The added value of commercial data is, although statistically significant, fairly limited.