Contact Us
CASE STUDY

Real-Time Recommender System for Enhanced User Experience and Efficiency

AT A GLANCE

A real-time recommender system was developed to replace the client’s batch-run model, reducing runtime by 90%, memory usage by 75%, and enabling immediate, user-triggered recommendations for enhanced efficiency and satisfaction.

Client information

Company Name
Financial Sponsorship Firm
location
London, UK
SIZE
Small Business
INDUSTRY
Financial Services
Services Provided
Real Time Recommendations
90%
Reduction in runtime, ensuring that recommendations are generated almost instantaneously, improving system responsiveness and user satisfaction.
75%
Decrease in memory usage, optimizing computational costs and improving system scalability, ensuring the system can process more user interactions.

CHALLENGE

The client’s existing batch-run recommender system was unable to keep pace with its growing user base, leading to delays in recommendation updates and negatively impacting user satisfaction. Users had to wait until the next day to see updated recommendations, which was not conducive to on-the-spot decision making.

SOLUTION

The recommender system was transitioned to AWS Lambda, enabling real-time recommendations triggered by user actions in the web app. Refactoring the script for modularity, optimizing memory usage, and storing updated distances in DynamoDB reduced runtime and memory usage significantly. Additionally, a robust deployment pipeline with a SQL database trigger ensured immediate processing and seamless integration, enhancing scalability and maintaining a responsive user experience.

IMPACT

    • Performance Enhancements: Achieved a 90% reduction in runtime and a 75% decrease in memory usage, facilitating a faster and more responsive system. These improvements significantly enhanced the platform’s ability to scale with a growing user base, ensuring seamless performance during peak usage.

    • User Experience Improvements: Eliminated next-day waiting periods for recommendation updates, enabling real-time interaction and satisfaction for users. This shift to on-demand recommendations has increased user engagement and improved decision-making speed.

    • Operational Efficiency: Streamlined interactions between the web app and the database, reducing overhead and potential errors. The introduction of automated triggers and real-time processing improved reliability and reduced the need for manual intervention, optimizing overall system performance.

TOOLS

AWS Lambda
DynamoDB
MySQL

Let’s Work Together

Ready to achieve measurable results? Tell us about your challenges, and we’ll show you how we can help

This field is for validation purposes and should be left unchanged.

Explore more

This site is registered on wpml.org as a development site. Switch to a production site key to remove this banner.