Binary classification models predict a binary outcome (one of two classes). Use this model type for yes or no questions. For example, you might want to build a binary classification model to predict whether a customer would buy a subscription. Generally, a binary classification problem requires less data than other model types.
Multi-class classification models predict one class from three or more discrete classes. Use this model type for categorization. For example, as a retailer, you might want to build a multi-class classification model to segment customers into different personas.
Regression models predict a continuous value. For example, as a retailer, you might want to build a regression model to predict how much a customer will spend next month.
Workflow for creating a classification or regression model and making predictions
The process for creating a classification or regression model in Vertex AI is as follows:
|1. Prepare training data||Prepare your training data for model training.|
|2. Create a dataset||Create a new dataset and associate your prepared training data to it.|
|3. Train a model||Train a classification or regression model in Vertex AI using your dataset.|
|4. Evaluate your model||Evaluate your newly trained model for prediction accuracy.|
|5. View model architecture||View the hyperparameter logs of the tuning trials and the hyperparameter logs of the final model.|
|6. Get predictions from your model||
If you want real-time predictions, you can deploy your model and get online predictions.
If you don't need real-time predictions, you can make batch predictions requests directly to your model.