Download our new whitepaper -"Comparing data science platforms for fault prediction in automotive applications"
Download our 25-page whitepaper to learn about
- The 4 sequential phases of analytics one can run on sensor data from automobiles
- Converting raw time series sensor data to a machine learning format
- Handling unbalanced data
- Capabilities of 5 data science platforms for predictive modeling: R, Python, RapidMiner, Spark and H2O
- Performance of 5 machine learning algorithms: Logistic regression, decision trees, random forests, SVM and neural networks
"One of the main objectives of "doing data science" on this sensor data is to be able to predict occurrence of automotive fault codes or fault detection. Based on these use cases, the predictions can be layered in several ways: we could be simply predicting the occurrence or non-occurrence of a fault, or we could try to be more specific about the type of fault code and the root causes. "