Case Study:Improving Shopping Experiences for In-stores customers with AI and ML

Customer operating consumer goods retail chain across the city of Munich, has a whopping number of yearly customer footprints all across its stores. They have been into selling of consumers goods for over five years now. Over the years, the retail chain has been successful to connect with the large pool of customers and maintained a flexible resonance with them.

Challenge

With the advent of smartphones and its compatibility to enhance user experiences, eCommerce is on a rapid growth scale. More and more businesses are going online to keep pace with the users and their demands. In such a scenario, physical stores are facing the toughest competition from these eretailers.  Since online shopping is one of the preferred means of shopping of today’s consumers, it is tough to survive and take the business to scale. As online shopping mania is not going to plummet in any time soon, rather it is to plunge a high growth rate in the coming years, retailers must find some improved ways to bring a change to traditional shopping experiences and boost their customer engagement.

All the retail stores need is a quest to become smart. But, it is not easy to go with the strategy yet. There are hurdles to it. In case with online shopping, the website owners can extract data about the customers and their shopping history with them. Based on the historical information, they use a unique approach to attract customers with their latest product offerings and entice them with attractive product discounts and other perks that could connect well with them.

This is the areas that fail most of the retail owners across the stretch and cause them to lose quite a good business in competition with the online commerce.

Problem our customer faced with their approach of selling was lack of information about customers and their interests towards specific products in the stores. Despite using effective marketing efforts with attractive discount ads at the shop fronts on special days, they were not sufficient to generate interest in them. Even though regular customers visited the in-stores, the sales representatives were not agile enough to engage with the customers and influenced them to buy.

Requirement

Customer wanted to implement a new technology to track customer behavior and their preference of items in the store. They were flexible tracking wifi and bluetooth signal data that could help them map potential customer traits all across the store using machine learning.

Solutions

SynergyLabs developed a few designs to be compatible with the store ecosystem and advised them to leverage our machine learning and deep learning capabilities to improve sales of their consumer goods items.

SynergyLabs uses AI to process different data collected from the location and customer activity  to classify unstructured data. They map data about customers based on their gender and age SynergyLabs also aims at transforming physical retail stores to help them become smart so as to cater to customer demands and enhance their experiences.

Designing the platform to use WiFi and Bluetooth Signals at optimal level 

First priority of our design application was to track the foot traffic of customers, assess their behavior and find errors in customer approach.

We tracked signals spreading across the store. We also intended to track signals from Wifi and Bluetooth at the entrance of the store and POS. 

After successfully tracking signals using machine learning API, the application was accurately detecting number of customers visiting the store throughout the day. Using machine learning , we were able to extract potential data and turned them into insightful algorithms. 

As our client logged in the system dashboard, they could have a better analysis of customer profile. Our AI powered applications enabled them to extract data and find meaningful resources behind it. As they better understand the customers based on their demographics and age, they classified the customers into age groups so as to collaborate with them more purposefully and offer better customer service. Our AI powered application helped them understand the number of visits of the customers by different time span and their shopping criteria. An extensive analysis of customer behavior helped them approach the customers and attract their attention with resourceful promotions and reduce the gap between their service hours and customers visiting hours.

 Results

SynergyLabs consultants helped the retail owner leverage the AI embedded API to the fullest and make exact utilization of the application in improving their customer service and boosting their sales.

Technologies used

Python, Scikit, and Tensorflow