What is an application or an app?

This article defines an application (app) in the AI & Analytics Engine

An app is a space created on the Engine for experimentation and operationalization of machine learning (ML) workflows. It’s usually aimed at solving business problems or tackling data science, analytics and machine learning (ML) tasks. During the app creation process, you'll be asked to define a problem, together with one or more related datasets. Currently, the following three problem types are available in the Engine:

1. Predicting the selected column from a dataset (classification & regression)

2. Finding groups of similar items by analyzing patterns in data (clustering)

3. Business templates

Within the app, you can solve a business problem from end to end (via templates) train a single model, or multiple models for the same task, and compare the results to choose the best-suited model. Depending on the app problem type, different features and functions are available.

Classification and Regression (prediction)

For Classification and Regression apps, a single train/test split is created from the dataset used to define the problem, common to all models to be trained. This allows you to compare their performance metrics fairly.

Classification and Regression apps contain:

• Feature Sets

• Models

• Deployments

You can define multiple feature sets to define the inputs to your model. You can also deploy trained models as a prediction API and make batch predictions with a tabular data file or make predictions real-time via the API endpoint.

Clustering (finding groups)

Clustering apps are defined by choosing the dataset they want to run clustering on, followed by choosing the columns that define similarity for its purpose. Under clustering apps, the clustering algorithms chosen at the time of creating the app are run on the entire data immediately, without any train/test split. Clustering apps produce a detailed result page for each algorithm run, containing the following insights:

• Overview: Number of clustered items, number of clusters, size of each cluster

• Analysis of the important dimensions that differentiate clusters

• A detailed description of the clusters in terms of the columns chosen

In addition, you can also download the clustered data or export it as a dataset to the same project.

Templates

Templates allow you to go through an entire workflow of predefined business problems.

Using a template is an efficient and quick way to utilize the power of AI to solve specific problems in a guided manner.

As an example, consider the Customer Churn Prediction template. The goal of this template is to create a model that can predict, on a periodic basis, the likelihood of churn (the risk) for the active customers of a company. The model utilizes either the transactional data or the subscription information of the customers to make predictions, depending on the nature of the business.

The template guides you to provide details about your business problem and builds all the necessary stages of the ML workflow. Specifically, it provides guidance in connecting to your datasets, the specification of the churn definition, and domain-knowledge inputs about contributing factors. It then automatically engineers predictive features from the data and trains the best models for churn prediction.

You can consume the results in many ways, such as analyzing the root causes of churn or deploying the trained models and scheduling periodical predictions. This allows you to stay informed about customers who are at high risk of churning, and take preventive measures if necessary.