U.S. Polo Assn. isn’t just a brand—it’s an experience. When you purchase U.S. Polo Assn., you own a piece of the sport of polo. Establishing its presence in the global market since the 1890s, USPA marks its history with an extensive collection of classic casuals. Today, USPA products are sold in over 300+ stores across the country.
Though USPA has its own in-store clienteling app which helps its executives communicate and guide visitors through their products, they were unable to strategically suggest relevant products to their consumers. This is due to the lack of an in-depth analysis of their customer’s likes and dislikes, thus the brand sought out Omuni’s expertise in analytics, customer profiling, and product recommendations.
The solution that we proposed applied collaborative filtering based recommendation system in the backend. This recommendation engine then provides the top five recommended products against each customer as soon as their mobile number is entered into the clienteling app. The recommendation of products is customized at the customer level for both existing and new customers.
The engine will automatically filter out the unavailable products and then pass on the recommendation to the system. In case any recommended product is unavailable in inventory, the most similar product will be pushed to the clienteling app.
The following crucial features helped in improving store walk-ins for USPA:
We study the behavior of each customer’s purchase pattern, and if any customer comes into the store, the engine maps his purchase behavior with a customer whose purchase pattern was the same. The engine then sends out the next best recommendations.
With omuni’s personalization capabilities, we analyzed the data and devised a strategy that pushes out perfect recommendations for USPA. This led to a 12% increase for in-store walk-ins.
USPA was able to send out product recommendations that led to an 8% increase in mall store walk-ins and a 12% increase in high streets
Identified: Lack of in-depth analysis of a customer’s likes and dislikes that results in loss of sale.
Developed: An advanced algorithm that provides store executives with recommendations for purchases.
Enabled: 12% improvement of store walk-ins across locations