Appian Tabular Prediction with SageMaker Reference App

Tabular AI prediction refers to the application of artificial intelligence techniques to structured, table-like data for making predictions or forecasts. Enterprise today has massive historic data, and the use of AI in this context, especially machine learning prediction models, can provide valuable insights and predictions from the data. Here are some common use cases included in the reference app:

1. Financial Services: In a role of a business analyst working for a company in the banking sector. Your goal is to predict whether your customer will repay the loan taken, or not.
2. Insurance: Multiple linear regression based on several features of individual against their existing medical expense to be used for predicting future medical expenses of individuals that help medical insurance to make decision on charging the premium.
3. Manufacturing: As a business analyst of a large manufacturing org, to predict which machine failure will occur in the future given a historical dataset that contains characteristics tied to a given failure type.
4. Marketing: As a business analyst of a large manufacturing org, to predict which machine failure will occur in the future given a historical dataset that contains characteristics tied to a given failure type.
5. Healthcare & Life Sciences: To predict predict the likelihood of diabetes in patients based on their medical history and demographic details.
6. Service: Predict the vehicle maintenance service given their historical service data

These are just a few examples. The key advantage of AI in tabular data prediction is its ability to uncover complex patterns and relationships within the data that might not be apparent through traditional analysis methods.

Appian tabular prediction with SageMaker reference app uses Amazon SageMaker Autopilot to automatically build, train, and tune the best custom machine learning (ML) models based on your data. It’s an automated machine learning (AutoML) solution that eliminates the heavy lifting of handwritten ML models that requires ML expertise. Users need to only provide a tabular dataset(csv format) and select the target column to predict, and Autopilot automatically infers the problem type, performs data preprocessing and feature engineering, selects the algorithms and training mode, and explores different configurations to find the best ML model. The problem type can be either binary classification, multiclass classification, or regression. This reference app is a collaboration with AWS and integrated with "SageMaker Autopilot sample solution"

Key features:

• Streamline SageMaker model creation, train, tune, and deployment
• Support endpoint and model deletion
• List all models with endpoints in one screen
• Administrative tasks such as remove model and purge endpoint of xx days old
• 6 use cases across 6 difference industries are included, along with their datasets, original dataset link with description, and model report to show model quality
• Use case datasets are provided in the download zip file

• add missing installation and user guide