Industrial Internet Application Development

Model generation process

During the model generation step as discussed in the previous section, the sample data will be divided into training and test data for building the model in ratios such as 70:30 or 80:20. Once data is identified, the next step is to identify the relevant algorithm applicable for the business use case and train the algorithm with the dataset, test, and then validate the model to the performance. This may take multiple iterations. Also, in some scenarios, multiple algorithms may be needed for the final outcomes.