Skip to main content

Machine learning: Personalized product recommendations and in store experiences

Updated over 3 weeks ago

AIQ leverages advanced machine learning models to deliver personalized product recommendations and in-store experiences tailored to individual customer behaviors. These models are trained using a comprehensive dataset that encompasses various customer touchpoints, ensuring a holistic understanding of customer preferences.

How to get recommendations via API

Get personalized recommendations for a contact ID


Data Sources and Model Training

Our machine learning models are trained on data from over 1,300 cannabis retailers, incorporating insights from multiple customer interactions, including:

  • E-commerce Interactions: Page views, clicks, and purchase history

  • Loyalty Program Engagements: Sign-ups, redemptions, and point accruals

  • Native and Web App Events: App usage patterns and event interactions

  • Website Analytics: Cookie and fingerprint-derived data

  • In-Store POS Data: Transaction details and staff interactions

  • Customer Demographics and Preferences: Including favorite stores and product preferences

By integrating data from over 50+ ecosystem partners, AIQ ensures that our models have a rich and diverse dataset, leading to more accurate and actionable insights.


Personalized In-Store Experiences

AIQ provides endpoints that allow retailers to customize in-store experiences based on the customer profile. For instance, if a majority of customers in a store prefer edibles, the in-store screens can be dynamically updated to highlight edibles and related promotions.

These personalized experiences can enhance customer satisfaction, increase average ticket size, and reduce customer frustration by presenting relevant products and offers.


Product Recommendations via API

Retailers can access personalized product recommendations for a specific customer by utilizing the relevant API endpoints. These recommendations can be filtered based on various criteria, such as product availability, customer preferences, and purchase history. Additionally, recommendations can be bundled with audience segments to target specific customer groups effectively.

For example, a retailer might receive recommendations for top spenders who have visited the store only a few times and have recently purchased a specific brand of edibles.

By integrating these personalized recommendations into the POS or e-commerce platforms, retailers can enhance the shopping experience and drive sales.

Did this answer your question?