1. Once we have followed the recommendations, we can go to prepare our model. Back to the target section, go to prepare a model and create a new model. In the model section we still have to make some more decisions. The first one is we want to use all features to  predict the target. In the data preparation window we have already removed the feature ‘PassengerID’ because it was an identification feature, but we have kept ‘Name’. Now when we are selecting the features we want to use to predict (then it will be called predictors) we can omit the feature ‘Name’. 
2. The second decision will be splitting the dataset in two parts: one for training the algorithm and the other for testing (measuring the accuracy of its prediction). 
3. We also have the possibility to select the algorithm and the accuracy parameter it’s going to use for its internal optimization. If you don’t select any, NextBrain will use an ensemble of algorithms to make the prediction.
4. Lastly, we can select the time we want the algorithm to spend to find the solution. Normally we are going to use short training  times but when we have very big datasets. Once we make this last decision we can train the algorithm.
5. When the algorithm is trained we can go to check if it has done it right and what insights can we get from its work. 
6. Under the ‘Evaluation’ button we will find the accuracy of the prediction. We can see for example a list of the features that have had more influence in the prediction and which haven’t had any influence at all. 
7. As an algorithm hasn’t to be a ‘black box’, we can check what are the troubles the algorithm has found to make this prediction. We can find it under the ‘Explainability’ button.
8. Inside explainability we will get more insights on our ‘problem’. For example, we will see a plot where all our data features are mapped into a two-dimensional plot in Dimensionality reduction. Then points are colored according to the target variable (blue and red color). A binary classification problem can be described as the separation of these points acciding its colors. If data points with different colors are mixed, the classification will be difficult. If we can see that different color points are more or less concentrated in different areas, the algorithm will perform the classification with high accuracy. 
9. In explainability we will see again which features have been more important for the algorithm to make this classification, and also in which range (Features influence). We will see that sex is the most important features and also the variable ‘Pclass’ (first class, second class or third class). We can understand that the first class cabins had wider and better connected corridors. They also had a separate deck from the other classes that had their own lifeboats. The model is telling us that a woman who traveled first class had a good chance of being saved.
10. In the ‘Evaluation’ window we can also predict if a certain combination of feature values will survive or not, and with which probability. 
11. Imagine we enter some data to make the prediction and the outcome is that this person will not survive. And you wonder why she/he is not going to survive. To better understand it you can check the ‘What if tool’. This tool basically looks for what’s necessary to revert the outcome. In our case, this tool will change some of the features in order to predict a survivor. For example, we enter the data for a man, 54 years old, second class (Pcclass), who has paid a medium fare. The result is that this man is not going to survive. We now check the ‘What if tool’ and the result is that instead of a man it was a woman, she could survive. Also that if he was an eldery man he could also survive or if he paid a first class fare too. We can also say that some features can’t change in our causal reasoning. For example, sex. So the what if tool allows to fox this feature value (man) and change the rest of the features. For example an eldery man or a man who paid an expensive fare for first class could survive.

Finally you can also make predictions directly on Google sheets. If you have a spreadsheet with the data used for the model open, you can click on ‘Predict’ on the side bar (you have to close NextBrain app and open only the sidebar), select the model (the model you have trained has a specific id number) and click on it. Automatically the target feature (‘Survived’) will be replaced by the model predictions with a formula. This formula is =PREDICT. So if you change a data point, the sheet will be refreshed and the  prediction will be updated.