Exploring Marketing Disparities Using Neural Nets

Talk Abstract: Point of sale tobacco (POST) advertising is an embedded element of the urban landscape of New York City. It's comprised of a variety of marketing practices including signs on the insides and outsides of retail stores and has a more immediate and comprehensive effect on tobacco sales than any other marketing channel. There is substantial evidence of disparity in the way tobacco products are advertised at the point of sale depending on the community demographic profile of focus. The goal of this project is to map POST marketing practices across New York City (NYC) using an automated method of detecting and classifying tobacco signage. In comparing the POST landscape with socioeconomic characteristics at the neighborhood level, the work also aims to explore marketing disparities and variable exposure of communities to tobacco advertisements. In this project, the state-of-the-art convolutional neural network, Faster R-CNN model has been used to identify signs and discriminate tobacco signages from other types of signs in NYC. Speaker Bio: Isha is a principal data scientist at Capital One. Prior to that, she worked at Ericsson as a data scientist. She completed her master's from New York University from an Urban Data Science program in 2018. She moved to the Bay Area in 2018 and before, worked in different NYU research labs (NYU Urban Observatory, NYU Audio Lab, etc.). Before moving to New York, Isha lived in Hong Kong for 5 years, where she did her bachelors from Hong Kong University of Science & Tech (HKUST) in Environmental Technology and Computer Science and later worked in HKUST- Deutsche Telecom Systems and Media lab (an Augmented Reality and Computer Vision focused lab) as a Research Assistant. Disclaimer: All views, thoughts, & opinions expressed in the webinar belong solely to the panelists, & not to the panelists’ employer, organization, committee, other group or individual.