This Small Business Innovation Research Phase II project aims to improve data mining technologies for location analytics. This project will focus on the analysis of semi-continuous GPS and/or WiFi-based location data generated by consumer mobile devices. The anticipated improvements would allow consumer insights professionals and advertising effectiveness researchers to better detect emergent patterns and to draw stronger inferences about consumer behaviors, preferences, and lifestyle attributes. The enhanced data mining system would utilize state-of-the-art pattern recognition and machine learning techniques to dynamically process and interpret location and other types of data. If successful, this research will impact the state-of-the-art in location analytics.

This research has the potential to meet the need of consumer insights professionals to better understand how consumers behave, without the use of lengthy surveys. In a broader sense, this research aims to accelerate progress in the emerging field of location analytics. This research can lead to the creation of a location analytics dashboard, similar to existing dashboards for web analytics. Most web analytics dashboards measure metrics such as site visits, page views and time spent for given online properties; analogously, the location analytics dashboard would measure visits by real consumers to physical locations. Such a location analytics dashboard could be offered on a subscription basis to companies that depend on consumer behaviors in the physical world ? including retailers, hotel/resort chains, restaurants, and travel companies. Such a dashboard would address a broad range of market research opportunities, from shopper loyalty research to store sitting to marketing effectiveness measurement. Additional future impacts of the proposed effort include the ability to integrate location analytics data into Geographic Information Systems for improved public safety, municipal planning and transit systems design.

Project Report

The impact of this work centers on improving the state-of-the-art for consumer/shopper insights and advertising effectiveness measurement. The technology developed under this award is helping businesses to better understand and engage with shoppers and more effectively target their marketing dollars. Specific outcomes of this work include the development of technologies to acquire and process high-quality location data from the GPS/WiFi chipsets of mobile phones. The aforementioned technology development efforts have been commercialized in the form of a market research platform that allows businesses to understand the "shopper journeys" of opted-in consumers and automatically trigger in-store mobile surveys to those consumers. Broader societal benefits of these technological advances include the future ability to combine GPS-derived consumer location analytics with Geographic Information Systems for improved public safety, municipal planning and transit systems design. Many state and local transit authorities conduct a "travel census" every decade; increasingly, GPS data is being used in addition to survey-based research techniques. Today, transit analysts manually sift that GPS data with minimal technological assistance. With the solutions developed under this grant, unlimited volumes of data can be analyzed with greater robustness and reliability. Transit authorities could use this research to identify locations that citizens are unable to readily access due to inadequate transit links, thereby suggesting a need for improved public transportation infrastructure. Similarly, this technology could assess the amount of time people spend in high-crime areas or districts where societal friction is endemic. Such insights would help urban planners to better zone new development districts. In terms of educational benefits, the emerging field of location analytics will in the future provide fruitful new ground for innovative research in academic institutions - primarily in marketing, media, urban planning, and geography departments.

Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Cadio Inc
United States
Zip Code