Customer Background

Our customer is an automobile designing house that designs premium cars and gives them an entirely new outlook.  They implement designs based on customer interests and requirements.

Project Background

The customer has a proven business model where an associate would address the unique requirements of their end-users one at a time and then create designs along with their recommendations to arrive at an end result. This requires a lot of time with multiple iterations. Since each customer has a different requirement, it isn’t idle to show them existing designs and the process thus becomes tedious. This resulted in increased overheads, decreased booking and increased waiting time for design selection and confirmation.


Automating the process of designing requires analyzing huge chunks of data and then recreating new designs which further complicates the process. Normal automation wouldn’t result in an output that would match customer expectations.


Our customer maintained a logbook detailing specific requirements their customers have and the corresponding designs finally selected. This is provided to new designers as a reference. We evaluated this and found the data to be pretty extensive and elaborate. This data was further analyzed and evaluated to arrive at different data sets that determine customer behavior patterns. ML models were then created to draw these trends and map them against the specific changes in designs. The system was designed to plot the characteristics within requirements and create design combinations that have proven to be successful. Each design generated included elements for designs that have been approved in the past and made sure they were unique. We did this by developing a flexible neural network framework, which could access different areas of car design and paint them with unique color combinations. The advanced model uses AI and ML to predict areas dark and bright, generating a perfect design that finally improves efficiency.


The waiting time for appointments reduced by 20% on average and reiterations were reduced by 15% resulting in improving the overall efficiency and customer retention.

Latest Case-study

Get a free quote