Skip to main content

Conclusion

Summary​

In this tutorial, you explored the process of building a time series model to forecast Net Promoter Score (NPS) using H2O Driverless AI. From accessing the necessary tools to configuring the experiment and interpreting the results, you learned how advanced machine learning techniques can enhance customer satisfaction strategies in the banking sector.

By following these steps,

  • You configured a time series experiment by applying automated feature engineering, model selection, and hyperparameter tuning to forecast NPS.
  • You interpreted key model outputs using interpretability tools to understand the factors driving NPS trends.
  • You evaluated the model’s forecasting accuracy through performance metrics and visualizations.

By completing this tutorial, you should now be equipped to confidently build and analyze time series models using H2O Driverless AI. For further assistance or to enhance your foundational knowledge, revisit Tutorial 1A: Introduction to H2O Driverless AI.

Feedback