Create a predictive model
In this part of the guide we will teach you how to create a predictive model, step by step:
The first step is to go to the ModelLab section in Predictto.
There, you must select the type of analysis you want to perform, in the drop-down menu that appears in the upper left. Remember to refer to the information provided at the article: ' What will I find in Predictto?', so you know which analysis best suits your needs.
Subsequently, if you wish, you can select a range of dates, so that your model considers only the data obtained within that range.
In the selection tree you will find all the types of devices, devices and parts of devices that you have registered on our platform. It's important to note that if you chose a type of analysis that uses information from measures (such as the calculation of degradation models), the selection tree will only show you devices that have one or more measures connected.
When you have selected the filtering parameters indicated in steps 3 and 4 , press the “Filter” button.
Now, you must select the source of the data that will feed your model. If you selected a degradation model analysis in step 2, the table on the right of the screen will show all the meters connected to the devices and parts selected in step 4. You must check the “select” box of the meter that you want your model to feed in. Remember that, if in step 3 you selected a date range, the model will only consider measurements made within that range.
Finally, appoint a name to the data group that you chose to feed your model. It's important that it be a descriptive name, since you will need it later to identify the model and consult the diagnoses derived from it. Once you have written the name, click on “Save and Analyze”.
By following the steps above, you will have already created a predictive model. Depending on the amount of data used to feed the model, the calculation time may vary. Our algorithms are optimized to reduce this waiting time to the minimum possible, and we are constantly working to improve in this point.
Once the model has been calculated, you can find it in the section Devices, where we will show you a list of all the existing models associated with your account, including the one you just created. By clicking on the name you gave to the data group used to feed your model, you can consult the results and diagnoses derived from it.
It's possible to select several measures at the same time, which will generate a predictive model for each one of them. In this way you can create many models with fewer steps and in less time. To perform the multiple selection you must use the 'ctrl' button ('command' on macOS) and select more than one asset.