Our Partner Case Study
Retail use case with Zomato
Zomato, a global restaurant aggregator and food delivery service, has taken steps to improve its recommendation systems and user experience. The goal was to provide more accurate and personalized food and restaurant suggestions to improve customer satisfaction and engagement on the platform.
Challenges
Faced with the challenge of efficiently processing vast amounts of customer data, Zomato needed a solution to deliver personalized recommendations in real-time. The goal was to develop a system capable of accurately predicting customer preferences and providing more relevant dining suggestions, ultimately enhancing user engagement and increasing order conversions.
Solutions Implemented
To improve personalized meal suggestions, a recommendation system based on advanced data analytics was developed, designed to predict customer preferences and provide real-time, relevant recommendations that increase engagement and conversions.
AI-Powered Recommendation Engine
An advanced engine has been integratedwhich uses advanced algorithms to analyze user behavior,
such as previous orders, search history and preferences. This has enabled Zomato to generate highly relevant and personalized recommendations for each user.
Dynamic
Customer Segmentation
By leveraging machine learning models, the solution dynamically segments customers based on their dining habits, cuisine preferences, and price sensitivity. This allowed Zomato to tailor recommendations to specific user segments, enhancing the relevance of the suggestions.
Real-Time
Personalization
The recommendation system was designed to update in real time, adapting to the latest user interactions. This ensured that customers received the most current and accurate suggestions, improving their overall experience on the platform.
Results Achieved
Significant
Increase in Recommendation Accuracy
The AI-driven system provided more precise recommendations, aligning closely with customer preferences, which increased user trust and reliance on Zomato’s suggestions.
Higher
User Engagement and Retention
Personalized and relevant recommendations led to higher user engagement, with more users exploring and interacting with suggested restaurants and dishes.
Improved
Conversion Rates
By facilitating downstream recommendations that matched customer preferences, Zomato saw an increase in order conversions, contributing to overall revenue growth.
We are currently using [BaseModel] for generating candidates to facilitate downstream recommendation systems. It generates recommendations using density-based rich customer representation. It allows us to trace customer lookalikes (‘People Like You’) to find similar users with similar cuisine/taste preferences as well as price affinity. We used [Synerise] Cleora for customer-restaurants graph data […] And to our delight, the embedding generation was superfast (i.e <5 minutes). For context, do remember that GraphSAGE took ~20hours for the same data in the NCR region. BaseModel give us a generalised framework for recommendations […] We are exploring ways to use it in other applications such as search ranking, dish recommendations, etc.
Data Science Team