Imputing relevant information from multi-day GPS tracers for retail planning and management using data fusion and context-sensitive learning

A. Moiseeva, H.J.P. Timmermans

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

Abstract

It is well known that the right location of shopping centres is of paramount importance. Unless stores succeed in attracting their own clientele, they rely to a large extent on the impulse behaviour of shoppers. To evaluate alternative locations, models of pedestrian behaviour may be useful. Modern technologies such as GPS and RFID offer new possibilities providing data on routes and stops, which are required as input for such models. An automatic interpretation of GPS tracers with respect to the activities being conducted could enhance the applicability of such technologies to retail management applications. This paper reviews this rapidly growing literature, and shows how automatic data imputation can be established by using Bayesian belief networks and how GPS traces can be fused with land use data of retail location.
Original languageEnglish
Title of host publicationProceedings RARSS Conference, Niagara Falls, Canada
Publication statusPublished - 2009

Fingerprint

Dive into the research topics of 'Imputing relevant information from multi-day GPS tracers for retail planning and management using data fusion and context-sensitive learning'. Together they form a unique fingerprint.

Cite this