Challenge:

Improve user retention and product satisfaction by providing more relevant gif content to user search queries, while at the same time reducing cost and time-to-market for product components such as facial recognition and sentiment analysis.

Solution:

Complete backend re-architecture using high-velocity microservices in Scala. Improved the existing monolithic PHP application that rapidly outgrew its original architectural capabilities.

• Built Tag Prediction API, Celebrity Detection API.
• Integrated Moments in Time model which recognizes actions on the gif as an additional search signal.
• iOS and Android SDKs for native performance on mobile.
• Cutting-edge ML for analytics.
• Developed iOS and Android Giphy SDKs that power your smartphone’s keyboard and all social apps.
• Top 3 search engine reimagined with deep learning and AI.

Result:

System capable of handling 100B requests a month. Also:

• Improved performance of blacklisting and whitelisting algorithm that sped up Overall Giphy API performance by 18%.
• Reduced the number of timeouts for Giphy API by 90-95%.
• Improved search service speed by 15%.