Data Mining Approaches for Assessing Chemical Co-Exposures Using Consumer Product Purchase Data

Consumer products are a potential source of near-field chemical exposures. Accordingly, the estimation of health risks from the use of consumer products is a public health concern for which toxicity testing and exposure models are important. A key challenge is the sparseness of information concerning who uses products and which products are used in combination. Our goal was to demonstrate a method to infer use patterns by way of purchase data. We examined the purchase patterns for three types of personal care products (cosmetics, hair care, skin care) and two household care products (household cleaners, laundry supplies) using purchase date from sixty thousand households collected over a one-year period in 2012. The market basket analysis methodology frequent itemset mining (FIM) was used to identify co-occurring sets of product purchases for all households and for demographic groups based on income, education, race/ethnicity and family composition. Our methodology captured robust co-occurrence patterns for personal and household products, globally and for different demographic groups. FIM identified cosmetic co-occurrence patterns captured in prior surveys of cosmetic use, as well as a trend of increased diversity of cosmetic purchases as children mature to teenage years. We propose that consumer product purchase data can be mined to inform use patterns for high-throughput chemical screening applications, and to inform aggregate and cumulative risk assessment.