Prediction of Failures in the Air Pressure System of Scania Trucks
Scania is a global company with sales of Trucks.The system in focus is the Air Pressure system (APS) which generates pressurized air that is utilized in various functions in a truck, such as braking and gear changes .To know whether the APS of truck is failure or not. An early detection of a failure in an Air Pressure System in trucks can save the company a lot money. This dataset is also a good opportunity to get a high level understanding of maintenance costs occuring in real-world Industrial environment . . Data contains 171 attributes and 60000 data points. . Highly imbalanced(59000 negative, 1000 positive) Visualized the data using PCA(Principal Component Analysis) & T-SNE LOGISTIC REGRESSION applied logistic regression and classified failures , using Roc curve found the best threshold that gives the cost of 27150.
RANDOM FOREST applied Random forest and classified failures , using Roc curve found the best threshold that gives the cost of 8870.
XG-BOOST applied logistic regression and classified failures , using Roc curve found the best threshold that gives the cost of 8680.