AI-powered Sponsorship Monitoring and Omni Channel ROI Calculation

Summary

An esports company based in Brazil needed an AI-powered solution to recognize sponsor logos within live streams on different social media platforms. They needed to monitor and track logo appearances during esports matches to calculate the ROI. Folio3 AI helped build this solution for our client that would process live stream videos and process them to detect logos and extract insights from the social media platforms in real-time.

About the Customer

A esports organization founded with a deep desire to represent esports. The company's history is characterized by innovation, significant achievements, and a commitment to tradition. Both inside and outside the virtual gaming world, they strive for strategic excellence to bring people together and ignite dreams.

Understanding the Challenge

Given their affiliation with various sponsors and brands, our client needed to monitor and track logo appearances during esports matches. They aimed to combine this viewer data with the logo appearance, which was integral for both sponsorship evaluation and engagement analysis.

Solution

Folio3 AI built a solution for our client that could detect multiple brand logos. The solution interface can process live stream videos to detect various logos and extract insights from social media platforms in real-time. The model was trained and fine-tuned on the data set provided by our client using computer vision and deep learning techniques.

• Customized AI model: The algorithm was fine-tuned and trained on the client data set and customized according to solution needs to detect various brand logos in real time.
• Real-time Logo Detection: The solution was able to detect logos and extract audience insights from live stream videos in real-time.
• Sponsorship Monitoring: By detecting logos at different locations in an event clip, our client was able to monitor and analyze the ROI for the event sponsors, counting how many times a logo was detected and how many users saw the logo
• Model Trained on 100+ Brands: The model was trained to detect logos of more than 100 brands from anywhere within the live streaming videos
• Insights Extraction and Sharing: At the end of a livestream, the extracted insights, i.e. (no. og logos detected and no. of views on each logo) will be saved on a database and shared with our client via a CSV file.

Result

At the end of a livestream, the extracted insights, i.e. (no. og logos detected and no. of views on each logo) will be saved on a database and shared with our client via a CSV file.