Extraction and Exploration of Business Categories Signatures
Published in Very Large Data Bases (VLDB) - Workshop on Big Social Data and Urban Computing (Bidu), 2018
Recommended citation: DA SILVA, Leonardo de A. ; Silva, Thiago H. . Extraction and Exploration of Business Categories Signatures. In: VLDB - Workshop on Big Social Data and Urban Computing, 2018, Rio de Janeiro. Proceedings of 44th VLDB, 2018.
View PDF
The proceedings was published on Springer’s CCIS
Abstract: Different business types may have distinct businesses functioning dynamics, ie, popularity times, that can be dictated not only by the service offered but also due to other aspects. Performing the business popularity time comprehension allows us, for instance, to use this information as a business descriptor that could be explored in new services. Recently, Google launched a service, namely Popular Times, which provides the popularity times of commercial establishments. In this study, we collected and analyzed a large-scale dataset provided by that service for business in different cities in Brazil and in the United States. Our main contributions are:(1) clustering and analysis of the collected business popularity times dataset in each studied city;(2) approach for identifying the signature that represents the behavior of specific categories of venues;(3) training and evaluation of an inference model for categories of establishments;(4) user evaluation of some of our results.