Predictive Analysis on Tracking Emails for Targeted Marketing

In this work, we present our experiences using a learning model on predicting the “opens” and “unopens” of targeted marketing emails. The model is based on the features extracted from the emails and email recipients profiles. To achieve this, we have employed and evaluated two different classifiers and two different data sets using different feature sets. Our results demonstrate that it is possible to predict the rate for a targeted marketing email to be opened or not with approximately 78 % F1-measure.

[1]  Xavier Drèze,et al.  Real-Time Evaluation of Email Campaign Performance , 2006 .

[2]  Dae-Ki Kang,et al.  Learning classifiers for misuse and anomaly detection using a bag of system calls representation , 2005, Proceedings from the Sixth Annual IEEE SMC Information Assurance Workshop.

[3]  Fu Duan,et al.  Application of Decision Tree Based on C4.5 in Analysis of Coal Logistics Customer , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[4]  Nebojsa Jojic,et al.  Bags of Words Models of Epitope Sets: HIV Viral Load Regression with Counting Grids , 2014, Pacific Symposium on Biocomputing.

[5]  Ayman Farahat,et al.  Econometric analysis and digital marketing: how to measure the effectiveness of an ad , 2013, WSDM '13.

[6]  Jim Sterne,et al.  Email Marketing: Using Email to Reach Your Target Audience and Build Customer Relationships , 2000 .

[7]  Ranjita Kumari Dash,et al.  Selection Of The Best Classifier From Different Datasets Using WEKA , 2013 .

[8]  Robert K. Plice,et al.  Toward a Sustainable Email Marketing Infrastructure , 2008 .

[9]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[10]  Tony Abou-Assaleh,et al.  Personalization of Content Ranking in the Context of Local Search , 2009, 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology.

[11]  Miguel Vargas Martin,et al.  Prediction Model Based on User Profile and Partial Course Progress for a Digital Media Learning Environment , 2012, DBKDA 2012.

[12]  Bruce M. Maggs,et al.  Posit: a lightweight approach for IP geolocation , 2012, PERV.

[13]  Xavier Drèze,et al.  Real-Time Evaluation of E-mail Campaign Performance , 2009, Mark. Sci..

[14]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[15]  Ludovic Denoyer,et al.  Predicting Information Diffusion in Social Networks Using Content and User's Profiles , 2013, ECIR.

[16]  Yiming Yang,et al.  An Evaluation of Statistical Approaches to Text Categorization , 1999, Information Retrieval.

[17]  R. Rettie,et al.  Email marketing: success factors , 2002 .

[18]  Rajesh Parekh,et al.  Learning to predict subject-line opens for large-scale email marketing , 2014, 2014 IEEE International Conference on Big Data (Big Data).

[19]  David K. Perry,et al.  Viral Marketing or Electronic Word-of-Mouth Advertising: Examining Consumer Responses and Motivations to Pass Along Email , 2004, Journal of Advertising Research.

[20]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Michael J. Pazzani,et al.  Learning and Revising User Profiles: The Identification of Interesting Web Sites , 1997, Machine Learning.

[23]  Yiming Yang,et al.  A Comparative Study on Feature Selection in Text Categorization , 1997, ICML.

[24]  Aleksandar Kuzmanovic,et al.  Towards Street-Level Client-Independent IP Geolocation , 2011, NSDI.