Table of contents

Industry accelerators

The industry accelerators that are provided by IBM are a set of artifacts that help you address common business issues.

Each industry accelerator is designed to help you solve a specific business problem, whether it's preventing credit card fraud in the banking industry or optimizing the efficiency of your contact center.

All accelerators include a business glossary that consists of terms and categories for data governance. The terms and categories provide meaning to the accelerator and act as the information architecture for the accelerator.

Some accelerators also include a sample project with everything you need to analyze data, build a model, and display results. The sample projects include detailed instructions, data sets, Juptyer notebooks, models, and R Shiny applications. Use these sample projects as templates for your own data science needs to learn specific techniques, or to demonstrate the capabilities of Watson™ Studio and other AI and analytics services.

Business glossary

A business glossary helps you describe your data with a standard vocabulary. You import categories and business terms as governance artifacts.

Audience
Data stewards and other users who are responsible for creating governance artifacts to govern data.
Contents
A set of business terms to describe data, with logical relationships between terms. See Business terms.
A category with the same name as the accelerator in which to organize the terms. See Categories.
Requirements
The Watson Knowledge Catalog service.
You must have the Manage categories and Manage governance artifacts permissions. To see which permissions you have, click your user avatar, select Profile and settings, and then view the Permissions page. If you need more permissions, contact your Cloud Pak for Data administrator.
Process overview
Each accelerator provides detailed instructions. These general steps provide an overview of the process:
  1. Import the category.
  2. Import the business terms.
  3. Publish the business terms so that they are available in all catalogs and during automated discovery.
  4. Assign business terms to columns in data sets with one of these methods:
    • Add business terms to a data asset in a catalog on the asset's Overview page. See Editing asset properties.
    • Some accelerators provide a Jupyter notebook that assigns terms to the data sets included in the sample project.
    • Run automated discovery so that business terms are automatically assigned to columns in the discovered data assets. See Discovering assets (Watson Knowledge Catalog).

Sample analytics project

An analytics project contains the assets that you need to build and train the models that are associated with the accelerator. You import the project with data science assets.

Audience
Data scientists or business analysts who analyze data and build models to solve business problems.
Contents
A readme file that provides instructions.
CSV files that contain the sample data.
Python 3.6 notebooks to train and score the models and associated Python scripts to prepare and transform the data for modeling. The notebooks include API endpoints to expose the output for the R Shiny application.
Machine learning models that are designed to help you find answers to the business problems described by the accelerator.
(Some accelerators) An interactive dashboard to show the results of the model.
Requirements
All users have permission to create analytics projects.
All accelerators that have sample projects require the Watson Studio service and one or more of these services:
To check which services you have on your platform, from the toolbar, click the Services icon. The services that show the Enabled tag are available. If you're missing services, contact your Cloud Pak for Data administrator.
Process overview
Each accelerator provides detailed instructions. These steps provide an overview of the process for sample projects:
  1. Import the analytics project. See Importing a project.
  2. Follow the instructions in the README to run the notebooks and perform other tasks.
Next steps
You can use the sample project as a template by adding your own data and following the same steps to go from data to deployed model. You might need to explore and cleanse your data. Because your data and schema are likely different from the sample data, the patterns that you find in your data will not match the patterns in the sample data. You can use the examples and code to adapt the model for your data and to retrain the model with your data.

To use a sample project as a template for your own data, follow these general steps:

  1. Add your data to the project.
  2. If necessary, cleanse or shape your data.
  3. Update and retrain the model with your data.

List of accelerators

Find the most up-to-date list of industry accelerators in the Cloud Pak for Data Community.

Accelerator Sample project Business glossary

Contact Center Optimization

Improve the productivity of your customer contact center by describing and characterizing your contact center data.

Industry: Cross-industry

None

The business glossary provides more than 100 business terms and a Contact Center Optimization category to organize the terms.

Credit Card Fraud

Quickly detect credit card fraud to reduce financial losses and protect you and your customers.

Industry: Banking and Financial Markets

None

The business glossary provides more than 135 business terms and a Credit Card Fraud category to organize the terms.

Customer 360 Degree View

Get a complete view of your customers by characterizing facets such as:

  • Customer segmentation
  • Credit risk
  • Loyalty
  • Social media sentiment

Industry: Cross-industry

None

The business glossary provides more than 110 business terms and a Customer 360 Degree View category to organize the terms.

Customer Attrition Prediction

Discover why your customers are leaving.

Industry: Banking and Financial Markets

The sample analytics project contains data science assets that enable you to quickly identify customers who are likely to churn so that you can get to the root of the problem.

Required services:

The business glossary provides more than 190 business terms and a Customer Attrition Prediction category to organize the terms.

Customer Life Event Prediction

Plan ahead for the financial wellness of your client by reaching out with the right offer at the right time.

Industry: Banking and Financial Markets

The sample analytics project contains data science assets to predict major life events, such as buying a home or relocating.

Required services:

The business glossary provides more than 170 business terms and a Customer Life Event Prediction category to organize the terms.

Customer Offer Affinity

Identify the right financial products and investment opportunities for new and existing clients.

Industry: Banking and Financial Markets

The sample analytics project contains data science assets to help you determine which offers are most relevant to your clients.

Required services:

The business glossary provides more than 200 business terms and a Customer Offer Affinity category to organize the terms.

Customer Segmentation

Easily differentiate between client segments by identifying patterns of behavior.

Industry: Banking and Financial Markets

The sample analytics project contains data science assets to divide your client list into meaningful segments.

Required services:

The business glossary provides more than 190 business terms and a Customer Segmentation category to organize the terms.

Demand planning

Manage thermal systems to produce accurate energy volumes based on anticipated demand and energy generation.

Industry: Energy & Utilities

The sample analytics project contains data science assets to optimize forecasts and decision making.

Required services:

The business glossary provides 190 business terms and a Demand planning category to organize the terms.

Emergency response management

Optimize the routes and deployment of the snowplows.

Industry: Cross-industry

The sample analytics project contains data science assets to advise on when to relocate which snowplows to minimize both the impact of the snow emergency and the relocation effort.

Required services:

The business glossary provides 20 business terms and an Emergency response management category to organize the terms.

Healthcare Location Services Optimization

Determine how far patients will travel to access quality health care.

Industry: Healthcare

The sample analytics project contains data science assets to understand patient behavior.

Required services:

The business glossary provides more than 70 business terms and a Healthcare Location Services Optimization category to organize the terms.

Insurance claims

Process insurance claims more efficiently to save time and money.

Industry: Insurance

The sample analytics project contains data science assets to predict the most likely outcomes and settlement amounts of accidental damage claims.

Required services:

The business glossary provides 50 business terms and an Insurance claims category to organize the terms.

Intelligent Maintenance Prediction

Reduce your costs by scheduling maintenance at just the right time.

Industry: Telco

The sample analytics project contains data science assets to optimize your maintenance schedule based on the costs that you will incur.

Required services:

The business glossary provides more than 100 business terms and an Intelligent Maintenance Prediction category to organize the terms.

Loan Default Analysis

Identify potential credit risks in your loan portfolio.

Industry: Banking and Financial Markets

None This accelerator includes more than 135 banking business terms and a Loan Default Analysis category to organize the terms.

Manufacturing Analytics with Weather (using SPSS and Cognos)

Use machine learning models and The Weather Company data to help you understand the impact weather has on failure rate, and identify actions that you can take to save time and money.

Industry: Manufacturing

The sample analytics project contains data science assets to quickly understand the leading reasons why there are high amounts of scrap on the production floor.

Required services:

The business glossary provides 120 business terms and a Manufacturing Analytics with Weather Data category to organize the terms.

Retail Predictive Analytics with Weather (using SPSS and Cognos)

Use machine learning models and The Weather Company data to help you understand how a retail inventory manager, marketer, and retail sales planner can quickly determine the optimal combination of store, product, andand weather conditions to maximize revenue uplift, know what to keep in inventory, where to send a marketing offer or provide a future financial outlook.

Industry: Retail

The sample analytics project contains data science assets to easily visualize which retail locations, products, weather conditions have higher predicted revenue uplift in sales based on season to improve product inventory planning and improve marketing campaign effectiveness, optimal inventory, and financial forecasting.

Required services:

The business glossary provides 100 business terms and a Retail Predictive Analytics with Weather category to organize the terms.

Sales Prediction using The Weather Company Data

Use machine-learning models and The Weather Company data to help you predict how weather conditions impact business performance, for instance prospective sales.

Industry: Retail

The sample analytics project contains data science assets to establish the path to financial success for your clients and your business by timely engaging stakeholders with relevant, reliable analytics for apt decision-making.

Required services:

The business glossary provides 75 business terms and a Sales Prediction using The Weather Company Data category to organize the terms.

Telco churn

Predict a given customer's propensity to cancel their membership or subscription and recommend promotions and offers that might help retain the customer.

Industry: Telco

The sample analytics project contains data science assets to provide real-time insights into personalized promotional offers most likely to lead to customer retention.

Required services:

The business glossary provides 45 business terms and a Telco churn category to organize the terms.

Utilities Customer Attrition Prediction

Discover why your customers are leaving.

Industry: Energy & Utilities

The sample analytics project contains data science assets to identify customers who are likely to leave.

Required services:

The business glossary provides more than 150 business terms and a Utilities Customer Attrition Prediction category to organize the terms.

Utilities Customer Micro Segmentation

Divide a company's customers into small groups based on their lifestyle and engagement behaviors.

Industry: Energy & Utilities

The sample analytics project contains data science assets to quickly identify customer lifestyle segments and engagement segments.

Required services:

The business glossary provides more than 170 business terms and a Utilities Customer Micro-Segmentation category to organize the terms.

Utilities Demand Response Program Propensity

Identify which customers should be targeted for enrollment in the Demand Response Program.

Industry: Energy & Utilities

The sample analytics project contains data science assets to identify enrollment prospects for the Demand Response program, in which customers agree to reduce or cycle down energy load during periods of peak demand in exchange for discounted rates.

Required services:

The business glossary provides more than 160 business terms and a Utilities Demand Response Program Propensity category to organize the terms.

Utilities Payment Risk Prediction

Identify which customers are most likely to miss their payment this billing cycle.

Industry: Energy & Utilities

The sample analytics project contains data science assets to identify customers who are likely to miss their bill payment so that the business can take preventive action.

Required services:

The business glossary provides more than 150 business terms and a Utilities Payment Risk Prediction category to organize the terms.