In the first blog of this series, using affinities to optimize promotions, we covered the key affinity metrics used to conduct a market basket analysis and determined optimal SKU’s (items) to pair for a promotion. From the example, it was found that breakfast sandwiches and energy drink categories were most purchased together, and importantly, the breakfast category drove the sale of energy drinks. The case study also went on to show at the item level that Monster 16 oz. energy drinks appeared in slightly more baskets with a breakfast sandwich than were Red Bull 12 oz. cans. So what else can we learn from this type of analysis? Taking it one step further provides more detailed information, such as average basket size and spend, the time when the purchases occur (hour of the day, day of the week, etc.), and the historical data to measure the impact of a promotional event. The following case studies will provide examples of how this can be applied:
Case Study #1:
Figure 1, below shows that the average dollar spend is $9.89 when a Monster 16 oz. drink and a breakfast sandwich are purchased together. According to csnews.com this is actually lower than the average convenience store transaction of $12.87, but higher than the average basket quantity of two or fewer items meaning shoppers are buying 1.8 more items on these trips. Retailers and suppliers can also compare two brands to see if one brand vs. another is more or less incremental to the breakfast sandwich category. It turns out, Monster 16 oz. is actually more incremental than Redbull 12 oz. given it has a higher average basket spend and item count.
Using the daypart chart below in Figure 2, we see that 55% of Monster 16 oz. + breakfast sandwich purchases are happening in between 6 a.m. and 7 a.m. It becomes evident that this type of shopper is on a breakfast mission, which generally means that purchases may follow a routine. With an average of 3.8 items purchased, and lower than average spend from above, we can gather that there is likely an opportunity to increase the basket size of this shopper with targeted promotions. It is also interesting to note that the occurrences by day of week increases on Thursdays and peaks on Friday for this type of purchase. Running more targeted promotions earlier in the week and supporting with appropriate media can help draw the shopper in, increase traffic, and in turn, drive sales around this item bundle. Additionally, strategically placing relevant items that correlate with the breakfast mission, or suggestively selling these items, can increase the chance the consumer buys additional items.
Once a promotion is decided on, affinity analytics can also be used to quantify the pre, during, and post impact of the event. In another example, a popular beverage brand ran a three month bundled promotion with a hot dog. The sales by month shown in Figure 3 below, clearly shows the spike in purchases during the offer period. In the latter two months of the promotion, the discount was increased, further propelling sales. The hour of the day chart Figure 4, illustrates that this product bundle is part of a “lunch-run” shopper mission and peaks at mid-week, however what is most interesting from this chart, is what we find happens after the promotion.
Post promotion, the incremental dollar value of this promotion can be quantified for the retailer. Figure 3 above, shows that after the promotion period, the baseline appears to have actually nearly tripled, indicating that appropriately bundled offers and in-store tactics to increase conversion on the right categories/products at the right time, have the ability to alter future shopper behaviors.
Affinities can provide a wealth of information about purchase behaviors, shopper missions, and indicate buyer preferences. This types of analysis helps retailers and suppliers understand what items are best to co-promote, timing of when promotions should take place, and also indicate optimal placement of categories or items. Furthermore, post implementation results are easily quantified. If you would like to learn more about affinities, please reference part one of the blog article here, or to learn more about how SwiftIQ’s Affinity tool can help, request a demo by clicking here.
OVERVIEW OF SWIFTIQ:
SwiftIQ uses high scale data processing and machine learning to deliver contextually relevant insights and digital experiences for retailers and brands. Its platform unifies and analyzes data primarily from in-store transactions as well as online behavior and third party sources to predict and inform category captains, shopper marketing, assortment, supply chain and content delivery decisions. SwiftIQ’s unique ability to process billions of basket-level transaction records in near real-time and convert that into on-demand mobile visualizations, dayparts, affinities and attribution fosters a new level of retailer/supplier collaboration and innovation.
Since launching its category captain and consumer behavioral analytics platforms in late 2014, SwiftIQ now analyzes over $60 billion in offline, receipt-level point of sale data. The company serves 5 of the global leading category suppliers and several billion-dollar retailers. SwiftIQ, named a Top Innovator twice by DataWeek, has also been recognized by Forrester, Forbes, NACS, ProgressiveGrocer and ComputerWorld for its achievements.