The vision of deploying a tactical algorithm for error detection quickly came about with the help of our dedicated team of data scientists and software developers. Since every successful initiative relies on full comprehension of the context and an honest collaboration, we made sure from the very beginning that we nurtured a strong and consistent communication of goals, needs, milestone metrics, iterations.
Hence, our team was involved in every software development phase, starting with prototyping the algorithms, evaluating them on test and validation datasets and, finally, deploying them into our client’s infrastructure. The communication bridge allowed our team to lead some of the most important decisions in terms of algorithms development, implementation and ongoing tuning, according to the established milestones.
The feature to error correlation implied a continuous monitoring of the qualitative data generated during the painting process. Based on the data provided by the client’s monitoring staff, our algorithms would analyze the data, detect if a certain combination of car body features or settings in the paint shop process leads to errors and notify the user about a possible error cause.
At the same time, we could develop the algorithms to also detect periods with high error concentration – having the data provided by the monitoring staff, the algorithm would analyze and detect which time frame was prone to having a higher error rate.
Our commitment to a highly qualitative customer experience translated into:
- Continuous researching of state-of-the-art analytical algorithms and solutions which could be integrated in the client’s product
- Proposing custom-built solutions for candidate algorithms
- Continuous communication in order to evaluate if our solution met our client’s goals