This project’s protagonist is a mobile data company that offers innovative solutions of mobile advertising and location intelligence. In order to achieve this purpose, it is essential to know precisely the behaviors and habits of users. For this reason we were asked to develop a deep profiling algorithm, able to classify users with respect to their offline behaviors.
Description and Benefit
The company has a considerable amount of positioning data that is received from the GPS or Wi-Fi systems of users’ smartphones. These geographical data are often incomplete and characterized by a significant degree of uncertainty. Through data mining and filtering techniques, Moxoff has processed the amount of data collected and then adopted data driven clustering algorithms that categorize user behavior based on their offline habits.
- Clustering, qualitative classification of users is accurate and automated
- Accurate and reliable information on the target, high precision profiling of users, based on places of interest visited by each individual
- Greater adherence of the campaign to the user’s interest, high effectiveness of the advertising campaigns, thanks to the more specific targeting and the recognition of possible unknown classes