Mercedes-Benz-benchtime-prediction

I addressed the problem of reducing the time that Mercedes-Benz cars spend on the test bench. As a leader in the premium car industry, Mercedes-Benz applies for nearly 2000 patents per year, making the brand the European leader among premium carmakers. To ensure the safety and reliability of every unique car configuration before they hit the road, I, as a company’s engineer, have developed a robust testing system. However, optimizing the speed of the testing system for many possible feature combinations is complex and time-consuming without a powerful algorithmic approach. The solution that I built used a dataset representing different permutations of features in a Mercedes-Benz car to predict the time it takes to pass testing. The tasks that I performed include loading and exploring data using pandas, identifying columns with zero variance, applying label encoder to columns containing categorical values, applying dimensionality reduction using PCA, splitting the training data into train and validation sets, fitting and predicting using different algorithms (xgboost and randomforest regressor), and measuring the performance using mean square error metric. This resulted in faster testing and lower carbon dioxide emissions without reducing Mercedes-Benz’s standards.