Start Date

12-13-2015

Description

Life events are often described as major forces that are going to shape tomorrow's consumer need, behavior and mood. Thus, the prediction of life events is highly relevant in marketing and sociology. In this paper, we propose a data-driven, real-time method to predict individual life events, using readily available data from smartphones. Our large-scale user study with more than 2000 users shows that our method is able to predict life events with 64.5% higher accuracy, 183.1% better precision and 88.0% higher specificity than a random model on average.

Share

COinS
 
Dec 13th, 12:00 AM

Reality-Mining with Smartphones: Detecting and Predicting Life Events based on App Installation Behavior

Life events are often described as major forces that are going to shape tomorrow's consumer need, behavior and mood. Thus, the prediction of life events is highly relevant in marketing and sociology. In this paper, we propose a data-driven, real-time method to predict individual life events, using readily available data from smartphones. Our large-scale user study with more than 2000 users shows that our method is able to predict life events with 64.5% higher accuracy, 183.1% better precision and 88.0% higher specificity than a random model on average.