Once the historical data is ready, we can now set up the model. In this example, we will use the monday.com board as a source.
First, let's go to the A.I. models page and press "Add". The new model window will appear:
Let's add the model name and choose "Forecasting". Next, you need to choose the type of forecast:
For our example, we will use the "Sales Forecasting" option. Then, the "Configure Forecast Model" option will appear:
By clicking on "Configure Forecast Model" we will launch the Wizard to set up our model. In step 1 we will choose the data source:
Pressing Next we will be guided to step 2 where we will need to set up the timezone and choose the data source from our project tool:
In the next step we need to configure columns:
Here is how our source board looks like:
Therefore, the mapping looks like this:
In the last step we have to do a final check. If all is ok, press Save & Close:
The system will mention that the model configuration is saved but the model training will be launched once you press "Apply" and save the model.
Press Apply and the model will launch the training. If you click on your model, it will look like this:
Once the model is ready, you will receive a notification via email. The notification example:
Now your model is ready to be used.
Monthly Sales model (till Dec 2016. First prediction data is 1/1/2017).