Pricing and markdown decision-making relies on factors such as demographics and psychographics of specific locations, and historical purchase analytics. Weather also is a vital factor in predicting demand for certain items, leading to more efficient pricing strategies. In an effort to provide streamlined tools for enhanced price optimization, Revionics, a retail life cycle price optimization solution provider, and Planalytics, a company focused on business weather intelligence, have announced new advancements to their joint weather-driven demand intelligence strategy.
The joint solution, integrated into Revionics’ cloud-based Life Cycle Price Optimization suite, allows retailers to make weather-driven forecasts that are more efficient, leading to more consistent pricing strategies.
“Weather is a significant and often dominant driver of demand for some product categories,” said Jeff Moore, VP of Science Development and Innovation at Revionics. “We wanted to offer the ‘de-weatherization’ of history, meaning that the effects of historical weather are accounted for in the demand models in such a way that they bring the models back to ‘normal.’ The Planalytics capability specifically is geared towards providing the differential impact of weather, or how much of the difference in year-over-year demand was impacted by weather.”
For example, Tractor Supply Company, a farm goods and ranch store brand and a Revionics customer since 2010, relies on weather data and predictive analytics to better adjust pricing based on consumer demand. Since implementing the Price Optimization solution in 2011, the retailer is able to examine and leverage the effects of weather by region more efficiently. According to a Tractor Supply Company spokesperson, going forward, “The solution will help us identify sales trends and take a more proactive approach to pricing by location, which will improve our margins and profitability. By utilizing this solution, we will have a deeper understanding of weather-driven trends and outcomes. Since Tractor Supply tailors to customers that are highly-impacted by weather — such as farmers, ranchers, horse owners, contractors, etc. — it is important that we have the capability to examine and leverage the effects of weather by region.”
Revionics and Planalytics have incorporated a variety of features to improve forecasting based on seasonal parameters, including:
• “De-Weatherization” of Data: Weather’s influence on historical sales of products by market and time are removed objectively, eliminating any possible error in historical weather-driven sales curves.
• On-Demand Weather Information: Retailers have the ability to view graphical images of historical and future weather trends then simulate different business scenarios for pricing, promotions and markdowns.
• Full Transparency/Visibility: In-depth information is provided regarding how weather is impacting pricing, such as the historical effect of weather on elasticity, seasonality and demand. This feature also provides insight into decomposition of elasticity, as well as the influence of raw demand versus one-time weather events.
“By understanding the impact of weather on demand, retailers can adjust their supply chain accordingly,” Moore said. “For example, when promoting weather-sensitive items, understanding the impact of weather on demand can be the difference between meeting demand, falling short or incurring massive overstocks.” Incorporating weather-driven demand into demand forecasts across our solution allows us to make all of our solutions and forecasts weather-sensitive.
“Incorporating weather-driven demand into demand forecasts across our solution allows us to make all of our solutions and forecasts weather-sensitive,” Moore added.
“By having access to more in-depth climate and weather-based analytics, companies can offer competitive or attractive pricing in situations where the weather is not helping to drive demand,” Frieberg said. “The ability to understand how weather influences consumer behavior — by category, location and time of year — offers a level of precision that ties in perfectly with localized pricing intelligence.”