Auto ML: Predicting Outcomes

Welcome back to Obviously AI university. 

In our last video, we walked through how to make our first AutoML model. In this video, we’re covering how to run predictions on your trained model. 

Let’s get started!

We’re using the same sample loan repayment dataset as before. We can see it has multiple columns that contain information such as customer’s id, age, income, loan intent, loan grade, and loan amount. This column, Status, is our prediction column. It indicates whether the loan was repaid or not. 

To get things going, we’ll click the predictions tab. This allows us to generate individual predictions on our trained model. We can also take a look at the model’s predictions on the test data. 

  • The predictions tab is where we can define what-if conditions. These are a way to understand what kind of business impacts can arise from changing one or more variables.
  • On the right, we can see the feature columns that were used when training our model. Now we can play around with different value combinations to ask different questions about our loan repayment data.
  • For text, we click on the dropdown and select a category. For numbers, we can input a number.
  • Each time we make a selection, the combination is assessed and a prediction is generatedinstantly. 
  • At the bottom of the predictions tab is Ideal personas. This gives us an idea of the ideal combination for each of the loan repayment classes. This means we can identify which type of user is most likely to pay the loans back on time.
  • Underneath Ideal personas, you’ll see Sample Predictions. This section details the model’s predictions on the test set.    With Obviously AI: 80% of the data is used for training the models and 20% of the data is used for evaluating the performance of the model. 
  • Under the predictions column here, you’ll see the model’s predicted value. Every time the model predicts the same value as the actual value, a “Correct” label is associated with the corresponding value. Similarly, if the model’s predicted value is different from the actual value, an “Incorrect” label is assigned to the value. 

Okay! We’ve covered a lot, so let’s do a quick recap of what we learned so far. 

In this video, we defined our what if conditions to predict outcomes in our model. This helps us understand and create many possible scenarios to predict what will happen. When we have these kinds of insights, we can proactively use them to preemptively strategize and make informed decisions, quickly. 

For further videos and educational content subscribe to our YouTube channel today to check out our Obviously AI University course and learn more about how you can leverage no-code AI to transform your business.

If you’d like to see Obviously AI in action, book a demo on

Complete and Continue