Machine Learning + Retail Execution = Supercharged Store Visits
And Data Analysis
Have you ever imagined how different your day would be if you had a dedicated personal assistant?
Someone who could arrive early and stay late, doing the administrative legwork so that you could
make the most of your time. Look no further than machine learning – an emerging technology that
enables computers to learn from and make predictions about data without explicit instructions.
For consumer goods companies, Machine Learning can ensure that field reps are routed to store visits more efficiently and empowered to manage daily tasks quickly. Imagine if you could deploy a robot to check the aisles for merchandising compliance, freeing up your human capital to focus on more value-added tasks. Saving time in store gives reps the opportunity to complete more visits, resulting in potentially significant cost-savings.
But Machine Learning does more than streamline store visits. It is an effective way of applying historical data to a problem by creating a model and using it to predict future behavior. Over time, machine learning identifies patterns and trends – like when a promotion works and with what parameters – that stakeholders can leverage to improve company strategy.
How can machine learning help CPG companies plan where to go and what to do, get more done with less data entry, and deepen data analysis?
Automate and Optimize Route Planning
A lot of work goes into identifying which points of sale must be visited, with what frequency, and what tasks to execute there. Imagine being empowered by software that considers multiple factors beyond geography to automatically predict the best time to visit a particular store and improve overall routing efficiency. If a store usually has a slump every July, recently hired a new manager, or has a new promotion coming up, the software will adjust routing accordingly to optimize employee time.
Machine Learning technology also generates tailored to-do lists for store visits that are based on what a particular store needs. So, before the rep gets to the store, they will be aware of issues like faulty equipment, out of stocks or phantom inventory and won’t have to spend time determining which tasks are required. Once reps arrive on site, the software can also help them streamline their audit activities.
Enable the ‘Perfect’ Store Visit
When the account reps are conducting a store audit, imagine having technology that helps them be more efficient with their time. Not only would they be able to avoid pen and paper – which 64 percent of retail execution professionals still use – but they could skip digital data entry by using image recognition and speech-to-text functionality. Digital image recognition allows reps to take pictures of product displays in the store instead of recording inspection results manually. From an image, a model can evaluate out-of-stocks, facings, prices, share of shelf, and planogram compliance. Whereas a human operator would have to visually assess each detail to find errant product placement, the software finds errors and inconsistencies in seconds.
Machine Learning also enables reps to verbally dictate notes, commands, and order placements to a wearable device such as a smart watch or headset. The system isolates key words from the dictation, which will trigger actions in the retail execution software. Digitally-captured data saves retail execution professionals time, and avoids the mistakes inherent to manual data collection. Data from the visits is disseminated in real time, so that managers receive audit results immediately instead of months after completion.
Deepen Data Analysis
Once the data has been collected, the final benefit of applying Machine Learning in retail execution is to find patterns in data that can help predict the best step to take next. CPG companies are dealing with enormous volumes of data on sales, store inventories, deliveries, and promotions at thousands of retail outlets. Using spreadsheets for tracking and analysis is time-consuming, and spreadsheets can only do what you tell them to do. But Machine Learning automatically identifies common patterns and trends that would normally be difficult to uncover.
For example, a Machine Learning solution can analyze data to predict the exact impact of a promotion in a major store chain, or determine the ROI of a loyalty program at a certain store. Understanding data at a granular level makes it easier to measure product performance, recognize issues, and scale best practices across the board.
Machine Learning can significantly help route field employees more efficiently, automate repetitive manual processes, and improve data analysis and insights across the organization. Ultimately, these benefits help companies keep up with the growth of their product market and make better decisions about promotions, campaigns, and investments.
Microsoft and AFS will continue to drive ongoing investments in Machine Learning and retail execution to help better position CPG companies for an increasingly digital age.
To learn more about retail execution solutions from AFS, click here.