Release Notes for Machine Learning - Application

Added integration with Plans. Use Plans to add new data from a workflow to an existing Machine Learning project. Learn more about ML integration with Plans.

Added the Correlations and Outliers panels from Data Insights to Problem Setup. You can nowquicklyview insights about your data before selecting a problem type.

Reduced the number of modeling workflow stages.You can find the previous Model Setup and Feature Engineering options in the Auto Model stage.

Redesigned the General tab to highlight metrics that drive business outcomes. Combined the Performance and Advanced Insights tabs to house all advanced metrics.

Added prediction intervals for all Time Series models in the forecast graph. Additionally, the downloadable forecast CSV file includes the prediction intervals.

Added the option to export your model as Python code in the Export and Predict stage. Export your model to evaluate the underlying code.

Renamed the Project Page to the Landing Page and updated the page design. Updates include a new page header, table styling, and a Machine Learning project icon. There is no change to existing functionality.

Previously, selecting All Projects would navigate to the Project Page (now called the Landing Page). Now, select the Machine Learning icon in the upper-left corner of the page to navigate to the Landing Page.

Added a link to Example Use Cases in AYX ML to the Additional Resources section of the Resources Pane. You can find the Resources Pane on the new Landing Page.

Streamlined the data prep and model selection process. You can now easily see your data and choose a machine learning method at the same time. Problem Setup replaces the Data Prep stage.

Added prediction intervals to Arima, Prophet, and Exponential Smoothing model types.To view the prediction intervals, go to the Time Series Forecast Graph located in the Export and Predict stage. Use prediction intervals to determine the confidence of a forecasted data point.

You can now easily select the columns you want to include in the modeling process and change column data types. To use this feature, select Manage Columns in the Prep Data stage.

Added a message to inform you if your data for prediction contains categorical values that were not present in your training data. The message details what those values are, and which columns contain them.

Added the ability to select which features you use in your model. This includes engineered features.To customize your feature selection, go to the Features tab in the Feature Engineering step. Reducing your feature count can speed up the modeling process.

Improved the speed of populating the Partial Dependence plot. On average, you can expect 50% faster load times.

Added the ability to upgrade individual projects to the latest AYX ML Runtime Version—and to revert back to your most recent version if you change your mind. You can find this functionality in the 3-dot menu on each project on the project page.

For a clearer workflow, we moved items from Data Insights to a new Model Setup step. Note that this doesn’t represent new functionality, just a new organizational flow.

Added an automated Feature Engineering step to Alteryx Machine Learning. This step allows you to apply primitives (generalized operations) to calculate new features. These features can improve model performance and help you gain further insight. Additionally, you can view the correlation values for the engineered features. Look for this new feature on the left side of the Alteryx Machine Learning interface.

We extended support for parsing real numbers (for example, 2.45 and 3.0) as integers. The parsing truncates the right side of the decimal point. For example, 2.45 becomes 2, and 3.0 becomes 3.

Added "Fourier Transform" and "Rolling Trend" primitives for improved Time Series feature engineering. We also added an additional 16 DateTime primitives for feature engineering.

Added 20 new DateTime formats and the ability to enter your own custom format. You can now use more DateTime datasets with our Time Series Regression model.

Added Time Series data validation to the Machine Learning Predict tool in Designer. The data validation checks if your input data length is longer than the forecast horizon.

Added an option to switch the axes of the 2-Variable Plot in the Correlations tab.

Expanded Pipeline Highlights in the Auto Model leaderboard for categorical and numerical operations. We now sort operations by order of execution in the model pipeline. Use this information to choose a model based on which operations we use in the model.

Support added for irregularly spaced Time Series datasets.

Added data checks to warn you when we modify your data.

You now have the option to set "time" as the stop criteria for model search completion. The minimum stop time is 1 minute.

Added Prophet to improve predictions for Time Series Regression models. This addition targets datasets with trends and seasonality.

Added ARIMA Regressor for Time Series Regression. ARIMA is a high performant statistical algorithm for Time Series datasets.

Updated the Stop button in the Auto Model search step. You can now stop the model search and select completed models up to that point.

Updated the Features panel in the Auto Model step to show all features contributing to your model. This helps you understand and evaluate models based on the features in use. In addition, features used in ensemble models are also shown.

A new data check identifies unary data type columns and automatically recommends next steps. This enables you to quickly detect columns to exclude from Machine Learning. The No Variance Data Check flags columns that contain only 1 unique value and then provides you with a recommendation to drop those columns.