To understand what drives digital first brand success, you first have to address how they differ from Brick & Mortar brands. Physical storefronts can rely on historical operations, brand recognition and foot / vehicle traffic. Most importantly they can control the customer relationship. Their customer is on-premise, they know who the customer is, can receive timely feedback directly from the customer and can immediately address any issues. With digital first brands, and delivery in general, restaurants mostly rely on delivery platforms that control driver priority and the customer relationship including feedback, loyalty and behavior. With less control over the process, understanding what drives digital first brands is more complicated to decipher and even more complicated to track.
In this blog post, we’ll explore how Nextbite uses data science to understand and optimize our delivery-first brand operations.
Mapping the overwhelming volume of incongruous data from the Delivery Service Providers was our first step, which is deserving of its own blog post. Combining that data with census and industry data we used a proprietary data science model to identify the factors that are statistically predictive. We then divided these factors into 2 camps, those a restaurant can control, such as operational metrics and hours of operation, and those that a restaurant can not control, like demographics, and proximity to employment hubs and nearby college campuses.
We continually refine and expand our model. We started with operational metrics, determining the relative importance of DSP rating, error rates, downtime, order delivery time and other factors. In subsequent iterations we added demographic data, determining the relative importance of average age, income, normalized population density amongst others. College enrollment and business presence were up next, followed by hours of operation, promotion and sponsored listing spend. We continue to refine our models by cuisine, adding late night delivery supply by location for brands that are more reliant on the late night day part.
Factor weights have differed by brand. Late night menus have a stronger normalized college enrollment coefficient while breakfast brands are more sensitive to business saturation. This is an iterative process where we continually test new factors. To find out more, join our inaugural Data Science Summit for Digital First Brands this March in Denver, CO.
Lara Hoyem, SVP, Data Insights
With nearly 25 years experience working at celebrated online consumer brands, Lara has helped grow digital businesses from start-ups to publicly traded companies. As Nextbite’s SVP, Data Insights, she is leading the company in its next phase of growth in the exploding delivery-optimized virtual restaurant category. Prior to joining Nextbite, she held key marketing and product leadership roles spanning ecommerce, subscription services, and ad-supported content publishing for companies including Study.com and Shutterfly, where she was most recently Vice President and General Manager, Photo Books, Calendars and Print. A consumer brand expert, Lara is passionate about working cross-functionally, using data for insights, developing sustainable differentiation for brands, and building deep customer relationships.
Rachel Boim, VP Data Strategy & Analytics
Specialties include multidimensional modeling, strategic data transformation, creative problem solving, classification, categorization & validation.