In-store vision analytics using StoreScript
No more sensors/Wi Fi/Bluetooth pairing with customers phones. All analytics are derived just by analyzing a feed from CCTV camera.
A solution which predicts footfall count before the day begins by using machine learning technology. Deep learning technology analyzes the video feeds coming through the CCTV cameras installed at the entry points and within the store and gives real time count analysis of people entering and leaving store 24 x 7 with their demographics like gender and age brackets. Dashboards of StoreScript illustrate where customers are spending more time, which corners are unnoticed and which sections are less visited. Confused customers are detected and the nearest sales executive is alerted on a smart phone to attend the customer. StoreScript’s Face recognition technology helps in identifying loyal customers so that the store manager can provide them personalised services.
StoreScript helps to take strategic decisions on a click, such as:
- the staffing pattern with customer flow
- Know peak opportunities for sales
- Identify seasonal trends
- Asses marketing campaigns
Count store walk-ins
In-store retail analytics are crucial to business owners to know what's happening in their own stores. One of the key insights is a store's conversion rate i.e. the percentage of customers who walk in vs. the people who do a purchase. These numbers offer insight into lot of factors. For example, high footfall means the store is attracting adequate potential customers but a low conversion rate indicates that it is not doing a good job of converting to sales.
Shopper’s behavioral insights
Analyzing how and where customers are spending time within the store indicates 'Hot' and 'Cold' zones on the shop floor. These patterns pinpoint optimal locations for high margin items that retailers want to push. Understanding the customer movement will highlight product exposure levels, engagement, and navigational routes throughout the store. Confused customers could be identified and personal assistance could be arranged immediately which can increase chances of sale.
Identify repeat customers
Face recognition technology identifies when customers are revisiting the store and the intimation is given to cashier/sales executive with a purchase history. This helps in striking a conversation with a customer to give a personalized experience. It could seamlessly integrate with loyalty management system to get instant information on previous purchases of the customer and give special promotions or recommendations.
Retail Promotions predictive analysis
Machine learning looks at the historical trends and patterns in data and can predict the deals/promotions which are most likely to get successful. Following are the ways predictive analytics can help in planning effective retail promotions. Targeted promotions . Planning . Personalization . Interactive visualization
It is crucial to predict sales by customer segments. Integrate behaviourial and transactional information of customers to strategize a customer centric promotion plan.
Observe consumers spending pattern and consider a retailer's share of wallet to identify price elasticity and know what shoppers are willing to pay.
Without predicting response to promotions by customer segment might lead to financial losses.
Following are the features where predictive analytics play a critical role
Duration of promotion
Best possible tactics for success of a promotion
Best possible deals to achieve the desired results Product placements on flyers
Make promotions more relevant to the customers by understanding their choices and preferences. Predictive analytics empower business to make decisions focused on customer engagement and develop personalized promotions through the channels that the customer prefers. This results in increasing loyalty in an increasingly competitive environment and increase the revenue.
Too many retailers are still making these decisions with a combination of spreadsheets and hours of human effort hence prone for errors. Faster decision making is possible only with interactive visualization. It facilitates business users in merchandising, marketing and category management can make quicker choices as well as empowers them with real time data.