Creating a General Purpose Predictive Model
Predictive models are ideal for doing exactly as their name suggests, making predictions. Some of the common use cases for predictive models are energy forecasting, sales projections, inventory management, or predictive maintenance.
Creating a Workspace
To start we must first create a new workspace (or add to an existing workspace, the steps are nearly identical, more information can be found here) by clicking "Create a New Workspace".
Now you will be given the option to name your new workspace and give it a brief description.
Now you can click "Continue" and we will upload our data.
Uploading Your Data
Once you have successfully uploaded a dataset you will be able to select the variables you are interested in comparing. Terrene defaults to General Purpose Predictive Model so you don't need to worry about switching the model type. Now you may select your input and output variables as shown below.
There are some important things to know about selecting variables for predictive models. First, is that with predictive models you can't have the same variable selected for both input and output. Also, for any machine learning model you want to avoid selecting any identifier variables (e.g. name, card number, email, etc.) these provide no information to the model as each identifier will be unique.
Once you have made your selections click "Finish" the model will begin training and you will be taken to the workspace dashboard where you can see the training progress and make predictions.