AI & Analytics Engine Knowledge Hub

Back to home

AI & Analytics Engine Knowledge Hub

Concepts

Concepts

Demystifying the Engine's features, concepts, and ML pipeline.

Projects

What is a project?

What are project roles?

Datasets

What data sources are supported by the Engine?

What are the requirements for dataset column names in the Engine?

What are column datatypes in the Engine?

Apps

What is an application or an app?

What is a template?

What is FlexiBuild Studio?

What is a machine learning-ready dataset?

When to use FlexiBuild Studio vs. a ML Solution Template

See more

Recipes

What is a recipe?

What are actions?

What is the formula editor and its capabilities within the recipe builder?

Feature Selection

What are estimated feature importance scores in the context of feature selection?

What is feature type?

How are features pre-processed for machine learning algorithms?

What is feature selection?

Machine Learning Problem Types

What Machine Learning problems does the Engine tackle?

What is regression?

What is classification?

What is binary classification?

What is multiclass classification?

What is clustering?

See more

Train/Test Split (Classification & Regression)

What is the train/test split for classification and regression apps?

What is a time-based split?

Models

What are algorithms in the context of building models?

What algorithms are available to build machine learning models on the Engine?

What is model training?

What is model overfitting?

What is hyperparameter search?

What is the Model Recommender?

What is the right approach for comparing and evaluating trained models?

Model statuses and their meaning

See more

Model Performance (Classification & Regression)

What is Prediction Quality and how is it calculated for the different ML problem types?

Which metrics are used to evaluate a regression model's performance?

Which metrics are used to evaluate a binary classification model's performance?

What are ROC and PR Curves for binary classification

Which metrics are used to evaluate a multiclass classification model's performance?

Evaluating machine learning models' performance in the Engine

See more

Model Insights

What is prediction explanation?

What are feature importance values?

What is What-If Analysis?

Evaluating clustering output results to get insights

Gain insights from predictions with Feature Importance, Prediction Explanation and What-If Analysis

See more

Prediction

What options are available for making predictions using FlexiBuild Studio

What is Batch Prediction?

Deployments

What does deploying a model mean?

Templates

What templates are supported on the Engine?

What does the customer churn prediction template provide?

What are the two types of churn supported within the customer churn template?

What options are available to define churn within the transactional option in the customer churn prediction template?

What options are available to define churn within the subscription option in the customer churn template?

What datasets are required to use the transactional option in the customer churn prediction template?

What datasets are required to use the subscription option in the customer churn template?

What do "contributing factors" mean in the customer churn prediction template?

How does the Engine process data for the transactional option within the customer churn prediction template?

How does the Engine process data for the subscription option in the customer churn template?

What features are generated after the Engine processes the data in a transactional customer churn prediction app?

What features are generated after the Engine processes the data in a subscription option in the customer churn prediction app?

What information is in the app summary for Machine Learning Solution Templates?

How are the top algorithms automatically selected to build models for the customer churn prediction template?

How are models evaluated for Machine Learning Solution Templates?

What are the predictions options for Machine Learning Solution Templates?

What does the prediction outputs contain for Machine Learning Solution Template?

See more