Start Date
10-12-2017 12:00 AM
Description
One of the prominent segments of mobile commerce is the mobile application market, where consumers download applications from an app store. Importantly, prior work showed that user behavior in mobile settings is substantially different than user behavior in PC settings, and therefore needs to be better understood. In this research, we study for the first time the predictive power of consumer engagement in such mobile settings. Using data from a leading commercial A/B testing platform specializing in app store design, we perform both in-sample assessment and predictive capacity evaluation of prediction models of app store conversion based on engagement information. Our findings show that in mobile settings, engagement-based models are highly informative for predicting conversion, and are consistent across different prediction methods (logistic regression, classification tree, and random forest). These findings indicate that engagement analytics may enhance our understanding of app conversion process.
Recommended Citation
Geva, Tomer; Reichman, Shachar; and Somech, Iris, "The Predictive Power of Engagement in Mobile Consumption" (2017). ICIS 2017 Proceedings. 7.
https://aisel.aisnet.org/icis2017/DataScience/Presentations/7
The Predictive Power of Engagement in Mobile Consumption
One of the prominent segments of mobile commerce is the mobile application market, where consumers download applications from an app store. Importantly, prior work showed that user behavior in mobile settings is substantially different than user behavior in PC settings, and therefore needs to be better understood. In this research, we study for the first time the predictive power of consumer engagement in such mobile settings. Using data from a leading commercial A/B testing platform specializing in app store design, we perform both in-sample assessment and predictive capacity evaluation of prediction models of app store conversion based on engagement information. Our findings show that in mobile settings, engagement-based models are highly informative for predicting conversion, and are consistent across different prediction methods (logistic regression, classification tree, and random forest). These findings indicate that engagement analytics may enhance our understanding of app conversion process.