“Why AI and ML are Key Ingredients for Quick-Service Restaurants”, an article posted on QSR, outlined several areas where machine learning insights and predictive analytics can offer operational improvements, financial benefits, and competitive advantages to businesses.
The article starts with “Despite the surge in takeout dining since the start of the pandemic, the quick-service restaurant industry is struggling. Labor shortages, supply chain problems, reduced in-store traffic, and rising costs have pushed the industry into a crisis. Coping with these headwinds requires a new approach to controlling costs, managing available labor, and improving customer experience. Artificial intelligence (AI) and machine learning (ML) technologies can help by leveraging data to optimize quick-service processes and operations.”
Planalytics provides detailed Weather-Driven Demand (WDD) metrics to several leading restaurant chains and the article outlined a few use cases that we do see clients addressing through ML and other forecasting and reporting solutions. Use cases include:
Aligning restaurant inventory to demand
QSR noted that “AI/ML technology can also optimize food purchasing, delivery, and inventory management to reduce waste, manage costs, and avoid shortfalls during peak demand times.”
Planalytics helps restaurants address this key priority with predictive demand analytics that precisely quantify the consumer’s relationship with the weather – the most volatile, immediate, and significant day-to-day external variable impacting sales. Weather-Driven Demand metrics or WDDs are ready-to-use, highly tuned, feature-engineered analytic that can be used to automatically make demand adjustments in a QSR’s current planning solutions and ML-based forecasting engines. Planalytics utilizes a combination of proprietary statistical and ML techniques that best optimize the predictive capabilities of WDD models. Planning accuracy improvements of 20% or more are common for specific products, locations, and time periods.
By better aligning location-level inventory with upcoming, weather-influenced demand shifts, restaurants can limit both lost sales from out-of-stocks (where sales will be elevated) and excess inventory (where sales will be depressed).
Optimizing labor resources
Another use case involves staffing, which accounts for a large portion of restaurants’ operating expenses. The article suggests that “a well-trained AI/ML application can benefit Quick-serves by helping them predict labor needs based on demand to optimize employee hours and labor spend accordingly.”
Labor remains a constrained resource for most QSRs and optimizing staffing schedules is one way address this challenge. WDDs can highlight when and where less staff will be sufficient to serve fewer customers. This can free up staffing hours to apply to other times when positive weather conditions will generate higher traffic levels and sales.
Insights for pricing & promotion
Predictive demand analytics can help businesses in these areas in several ways. The QSR article highlights how analytics can be used to reduce food waste. “AI/ML system that’s tracking inventory levels and stocking dates can also suggest discounts or promotions on menu items when there are overstocks of perishable ingredients, to prevent waste. This can be especially beneficial given that 931 million tons of food is wasted at retail and consumption stages and the average cost associated with food waste is around 5.6 percent of total sales.”
Once again changes in the weather can significantly alter restaurant traffic levels. By incorporating Planalytics WDD analytics into ML or other demand forecasting platforms, businesses can minimize waste before it gets to the kitchen by reducing orders where unfavorable weather will negatively impact sales.
Knowing how the weather will be impacting consumers is also a great way to optimize promotions and digital marketing. Targeting campaigns on markets where positive weather impacts mean your advertising will resonate more with an audience has generated substantial ROAS (return on advertising spend) gains.