Large-scale characterization of co-purchased food products with soda, fruits, and vegetables: association rule mining on longitudinal loyalty card grocery purchasing data in Montréal, Canada. (Preprint)

BACKGROUND Foods are not purchased in isolation but are normally co-purchased with other food products. The patterns of co-purchasing associations across a large number of food products are not known. OBJECTIVE To quantify the association of food products purchased with each of three food categories of public health importance; soda, fruits and vegetables using Association Rule Mining (ARM). METHODS ARM was applied to grocery purchasing baskets (lists of purchased products) collected from loyalty club members in a major supermarket chain between 2015 and 2017 in Montréal, Canada. A selected subset of co-purchasing associations identified by ARM was further tested by confirmatory longitudinal (shopper-level) regression models controlling for potential confounders of the associations. RESULTS We analyzed 1,692,494 baskets. Salty snacks showed the strongest co-purchasing association with soda (Relative Risk[RR]=2.07, 95% Confidence Interval[CI]: 2.06, 2.09). Fresh vegetables and fruits showed considerably different patterns of co-purchasing from those of soda, with pre-made salad and stir fry showing a strong association (RR=3.78, 95%CI|:3.74-3.82 for fresh vegetables and RR=2.79, 95%CI:2.76-2.81 for fresh fruits). The longitudinal regression analysis confirmed these associations after adjustment with the confounders. CONCLUSIONS Quantifying inter-dependence of food products within shopping baskets provides novel insights to develop nutrition surveillance and interventions targeting multiple food categories, while motivating research to identify drivers of such co-purchasing. ARM is a useful analytical approach to identify such across-food associations from large transaction data.