ProCogia’s data science team, leveraging their expertise in Advisory, Data Science, BI & Analytics, and Data Engineering, using tools like Python, SQL, and AWS, approached this challenge with a new idea. They recommended integrating mechanic notes as a novel data layer, enhancing the training of their models. This approach not only provided a more granular understanding of each vehicle’s condition but also introduced a previously untapped data source: car history and mechanical information.

The redesigned recon models incorporated this new data set, transforming qualitative mechanic insights into quantifiable metrics through a sophisticated vector matrix. This enhancement allowed for a more nuanced and accurate prediction of reconditioning costs. The result was a model that performed 50% better than its predecessor, with a D2 Tweedy score improvement from 0.26 to 0

The enhanced recon model had a tangible impact on Canada Drives’ operations. It not only streamlined the cost allocation process but also introduced a level of precision that was previously unattainable. This improvement translated into better pricing strategies, increased operational efficiency, and a competitive edge in the used car market. In an innovative twist, ProCogia demonstrated the potential of integrating computer vision to assess the condition of used vehicles. This technology could revolutionize various aspects of the buying and selling journey, offering insights that are both rapid and reliable.