The landscape of in-store observation solutions

heatmap pickups and returns

With the increase in adoption of in-store observation as a means to improve products and improve shopping experiences, and as a consequence of the realization of its potential in delivering timely and comprehensive information, technology has been pushed to further remove barriers and enable the delivery of the next level of insights to create the perfect shopping experience.

Store-level observation (macro analytics)

Location and proximity based solutions, leveraging technologies such as RFID, wifi, and iBeacons, led the way to unlocking the understanding of store-level metrics (macro analytics), followed by the use of security cameras and 2D sensors. Counting store visits, tracking dwell times, and characterizing return visits; these solutions are helping retailers answer significant questions regarding the performance of their investments in bringing shoppers to the store, and increasing the size of their baskets.

Enabling the generation of store-level (macro) insights has not been completely friction free. RFID and analysis of video are still facing implementation time and cost challenges. Wifi and iBeacons depend on shoppers having smartphones with wifi or bluetooth enabled, and in the case of iBeacons, an iBeacons enabled application running in the background, which impacts the number and potentially characteristics of the shoppers included in the research.

At Shopperception we have chosen 2D sensors to deliver macro analytics, which provide comprehensive and accurate coverage of all visits, as well as a cost effective alternative for grocers, pharmacies and cosmetics.

Category-level observation (micro analytics)

Understanding shopper behavior in the category is much more complex, as it requires capturing what every shopper is doing at the shelf, in the aisle, with each product, at every location it is offered in the store. In the case of micro analytics, video mining led the path, starting with manual post-processing of video feeds, followed by automated processing of the same. 3D sensors entered the market targeting video games, but have proven to be a great enabler of category-level in-store observation.

Micro-analytics has not been challenge free either. In the case of video mining, accuracy, implementation time and cost continue to be the primary concerns. In the case of 3D sensors, Shopperception’s main technology, we have seen the main test to be with retailer adoption, which continues to ease as the benefits become obvious.

Category-level observation is enabling both retailer and manufacturers improve their overall positions, by gaining deep understandings of the way shoppers interact with products in the aisle, how they make decisions in front of the products, and what are the main drivers for such decisions. Retailers and manufacturers are also gaining a much deeper understanding of the competitive dynamics at the shelf, as well as the effectiveness of end-caps and multiple placement of products in the store. Planograms and in-aisle activation are being fine-tuned before making larger investments in chain or region wide rollouts. Product launches are being guided by in-store testing, and category reinventions supported by actionable insights from real shoppers, shopping in real stores, under passive observation.

Here is a sample of a Category Assessment by Shopperception, that shows the evolution of micro analytics:

Category Assessment sample (sample deliverable)

Feel free to reach out with comments and questions, or join the conversation!

See you in the store!

Read previous post:
Let’s do some in-store testing…

Brands and retailers constantly face the uncertainty of how changes to stores, to categories, to products, will impact the performance...