User-level incremental conversion ranking without A/B testing
The traditional approach to build incremental conversion prediction model has to rely on A/B test results. However, under certain intense business environment, A/B testing can be limited by technical support, platform, or budget, and become not practically available. In this paper, we propose an algorithm to rank users by incremental conversions resulted from advertising effects, which is based on user’s conversion history and the output from a conversion prediction model. By appropriately defining who an active user is, this algorithm is proven to work well with real data. In case where an A/B test is not available and incremental conversion-based user targeting is desired, this algorithm offers a practical solution.
KeywordsUser targeting Incremental conversion Machine learning Business intelligence Big data
We are grateful to the support of Oath field marketing data science and analytics organization for this study. It is a great pleasure for Y. Liu to dedicate this paper to his Ph.D. supervisor, Prof. Mo-Lin Ge, on the occasion of his eightieth birthday.
- Bell, R., Y. Koren, and C. Volinsky. 2007. Modeling relationships at multiple scales to improve accuracy of large recommender systems, in Proceedings of KDD’07, pp. 95–104, San Jose, California, USA, 2007.Google Scholar
- Gordon, B., F. Zettelmeyer, N. Bhargava, and D. Chapsky. 2016. http://www.kellogg.northwestern.edu/faculty/gordon_b/files/fb_comparison.pdf.
- Kumar, S. Optimization Issues in Web and Mobile Advertising, in SpringerBriefs in Operations Management, (New York: Springer, 2015). https://doi.org/10.1007/978-3-319-18645-0_2.
- McKinsey, and Company. 2016. Global Media Report, http://www.mckinsey.com/∼/media/McKinsey/Industries/Media%20and%20Entertainment/Our%20Insights/Global%20Media%20Report%202016/GMO%20Report_2016_Industry%20overview_v3.ashx.
- Pechyony, D., R. Jones, X. Li, and D. Cerrato. A joint optimization of incrementality and revenue to satisfy both the advertiser and the publisher/ad network, https://pdfs.semanticscholar.org/0fac/cd336b65d7c512626280e41f5f581621c0f0.pdf.
- Shao, X., and L. Li. 2011. Data-driven multi-touch attribution models, in Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 258–264.Google Scholar
- Spark Machine Learning Library (MLlib) Guide. 2017. https://spark.apache.org/docs/2.1.0/ml-guide.html.