About Me

I’m Cameron Bale, a fourth year Ph.D. student in the Decision Sciences department at Drexel University, Philadelphia, PA. I have a broad background with training in economics, statistics, optimization, and computer science. I am a passionate researcher who loves to code, listen to music, lift weights, spend time outdoors, and relax with my wife and our two daughters.

Research

My research interests lie at the intersection of data privacy, statistics, machine learning, forecasting, and the law. In general, I study and develop data anonymization methods that preserve data subjects’ anonymity and sensitive information without severe reductions in data utility. My goal is to help businesses maintain the utility of their data for its intended use case(s) while improving privacy for data subjects.

My coauthors and I recently published a paper in Expert Systems with Applications in which we protect the identities of the authors of online reviews by generating synthetic attributes (e.g., location and rating) to accompany their posts. A copy of the paper can be found here.

I have several working papers, most of which are related to data privacy. The first takes an empirical approach to examining the effects of privacy protection on the accuracy of popular forecasting models. We propose a novel matrix-based privacy method which swaps the values of time series with similar features (e.g., strength of trend and seasonality), and offers a much better privacy-utility trade-off than existing privacy methods (e.g., differential privacy) for forecasting. A draft of the paper can be found here. This paper is currently under review at International Journal of Forecasting.

Two other working papers are focused at the intersection of data privacy legislation and privacy methods. The first, which received a first-round revision at Transactions on Data Privacy, is a multi-disciplinary effort to use existing data privacy literature to provide reasonable interpretations of anonymization criteria for location data described under the GDPR. The focus of the second paper is an automated data synthesis method for legally anonymous synthetic data, which we illustrate in an application to location data from South Korean COVID-19 patients. We plan to submit this paper to the Journal of the American Statistical Association.

My final paper is in another research area entirely and is a continuation of my RA work as an undergraduate student. We are examining the effects of Category Captainship for various retail product categories. Our results will have important implications for ongoing collaboration between retailers and product manufacturers in determining product assortment, product display layout, and ongoing relationships between the retailer and other category partners. We plan to submit this paper to Management Science.

I am advised by Dr. Matthew Schneider, whose feedback has been instrumental in guiding my research.

Background

I received a B.S. in Economics with a minor in Statistics from Brigham Young University Provo in 2019. During my time there, I worked with Dr. Jeff Dotson on the previously mentioned Category Captainship project. I began my Ph.D. training at Drexel in August of 2019.