The Client
Being an INC5000 honoree, McQueen Autocorp is a leading US-based used car selling company with a buyer network spread across the entire United States.
McQueen Autocorp offers a nationwide modern car selling service, facilitating sellers with an instant offer for their car(s) using price prediction algorithms and real-time bids from an extensive network of licensed buyers. With 600,000 vehicles sold annually, McQueen Autocorp has seen a 300% increase in reve-nue over the course of 3 years.
Disclaimer - The name McQueen Autocorp is a placeholder as there is an NDA signed between both parties.
Challenges
Our client struggled with managing the high volume of car images uploaded by sellers..
- Around 120,000 images were uploaded monthly, many containing inappropriate content.
- Manual approval by a 15-person team was time-consuming, error-prone, and impacted customer experience.
Solution
We implemented an AI-driven solution to automate the image verification process.
- A Computer Vision model was trained to classify images as cars or non-cars, flagging irrelevant ones and notifying the team via Slack.
- The model cross-checked the car's make and model in the image with the user-provided details, flagging any mismatches for manual review.
- After training with 1,500 images, the model achieved 85% accuracy, and human agents were involved when the confidence was below 80%, improving the model over time.
Results
The solution streamlined the image verification process, enhancing both accuracy and efficiency.
- The model’s accuracy increased to 90% after six months of feedback and upgrades.
- Errors were reduced, leading to faster approvals and better quality control.
- Manual review time was cut down, improving user experience and bolstering the brand image.
