How AI is Redefining Direct Store Delivery
We often talk about how to make retail shelf replenishment easier on store employees. But as these responsibilities increasingly shift to direct store delivery (DSD) drivers dispatched by consumer packaged goods (CPG) companies or manufacturers, it’s important we think about what they need to do their end-to-end jobs more efficiently—from the moment they wheel pallets off their delivery truck to the moment they finish the restock, issue a receipt to the store associate and head to the next stop on their regular route.
Stocking the Truck Better Keeps Shelves Fully Stocked
With limited space on the truck, and variable demand patterns affecting different stores, you must optimize your delivery system to assure every retail outlet consistently maintains right-sized quantities—or optimal stock position—across every SKU, particularly for perishable foods.
As an example, let’s consider the challenges within one major grocery category, bread:
Fresh bread has a relatively shorter shelf life. Major bread companies have typically conceded an intrinsic (or dare I say it, baked-in?) return rate of 6-7% of their product as it passes its sell-by dates on store shelves. With the razor-thin margins of grocery products, waste reduction—shrinking that spoilage rate however possible—has become an important key performance indicator (KPI) in this space.
In this age of instant gratification, where new product categories rapidly redefine the marketplace, bread consumers in particular tend to be quite discerning. Those who aren’t fiercely brand-loyal may still be motivated around health-driven options—whole wheat, organic, non-GMO and so forth. When their preferred choices become chronically understocked at one grocer, they’ll eventually seek them out among competitors. Grocery retailers rely upon the efficiency of DSD CPGs to retain both customers and revenue.
Demand patterns for baked goods are hyperlocal, influenced in large part by consumer demographics and store attributes. Other key variables – seasonality, holidays, events, price changes, product transitions, and new product introductions – make it even harder to predict true, unconstrained consumer demand.
With so many variables in play, where can advanced AI/machine learning (ML) data science factor into a predictive ordering tool? How could you successfully leverage a wealth of data sets to optimize on-shelf availability across every retail outlet, while minimizing waste?
In my experience, an ideal solution would revolve around five key points:
Generate an unconstrained statistical forecast at a day/store granular level, augmenting statistical baselines with emerging demand variables that AI can track in real time. This might include seasonality (in the case of bread, demand for sandwiches during the back-to-school period), retailer promotion schedules, even localized weather conditions.
Automatically convert those forecasts into optimal/suggested order quantities, leveraging business rules and inherent DSD constraints such as tray rounding, service days, and material availability.
Perform exception-based reviews, spanning various dimensions such as customer and route, as well as incentivizing drivers’ performance for speed and efficiency.
Include capabilities to make late adjustments on-the-fly, based on perpetual inventory recommendations and in the field last-minute insights.
Drive business performance by measuring KPIs throughout the lifecycle of the product. Facilitate rapid corrective actions around business decisions or model tuning.
The Proof Is in the Pudding (or Pie)
The technology behind DSD predictive ordering has already made huge strides, thanks largely to leading-edge AI/ML innovations. Specifically, dynamic aggregation algorithms, leveraging cloud-scale computing power, are successfully refining enormous volumes of data at a time series level. This ultimately gleans the most actionable data points into what we term the optimal order—or the right-sized quantities for every DSD deliver route. It’s driven by AI forecast and visibility into components such as base, promotion, seasonality, and more.
This data can be directly accessed by delivery drivers and other front-line personnel via a tablet-based user interface, an essential tool for every driver as they efficiently service every stop along their daily delivery routes.
Over the past few years, we’ve witnessed the continuing evolution of grocery DSD firsthand, as antuit.ai customers already account for an overwhelming majority of the retail bread market in North America, spanning iconic brands as well as popular niche products. The innovation of AI-powered predictive ordering that has already helped redefine the baked goods space can also be successfully applied across multiple other consumer goods categories as well.
Contact us to learn more.
Jasneet Kohli
Jasneet Kohli is head of antuit.ai’s Solution Consulting for Zebra and has more than 15 years of experience generating value for consumer products companies and retailers. He has held various leadership roles across business operations, solution strategy, and customer success. Previously, he served as head of procurement and logistics for Abbott in Singapore and Managing Consultant for IBM.
