What are the types of Business Analytics?

Depending on where you look, you may see different posts stating that there are three, four, five or more types of analytics. So how many are there? There are three types of business analytics that are consistent among different sources: Descriptive, Predictive and Prescriptive.


Answers the question: “What has already happened?”

Descriptive analytics is the most basic form of analytics and usually the first type of analytics utilized by businesses. Descriptive analytics attempt to describe what has happened in the past. It does this by looking at historical data presented in a manner that is easily digestible such as reports, charts, dashboards, scorecards, etc. Most of the data that you see today are descriptive analytics.


  • income statements
  • balance sheets
  • most information on your car’s dashboard: mpg, odometer, average speed
  • school report cards
  • fitness tracker applications

Depending on how this data is presented you can begin to identify trends, comparisons and changes from period to period. Descriptive analytics do not tell you anything about future performance or the likelihood an event will happen.


Answers the question: “What might happen?”

Predictive analytics can use most of the same data that make up descriptive analytics and attempt to predict probable futures based upon historical performance. You will notice that predictive analytics uses words like “might happen” or “probable” and not “will happen” and “certain”.

Everything is possible and Nothing is certain

The above quote demonstrates the point of predictive analytics – the fact that we cannot look into a crystal ball and determine the inevitable future, we need a way to determine on a scale from “Will Not” to “Will” how likely something will happen – this is done with probabilities.  Since nobody knows what will happen, probabilities exist to protect you against your guesses about the future.


  • business earnings forecasts
  • other information on your car’s dashboard: remaining mileage based on fuel
  • exit polls to predict election winners

Knowing that an event is likely or unlikely to happen – what can you do to take advantage or hedge against the event?


Answers the question: “What can I do about it?”

All organizations utilize at least one outcome of prescriptive analytics (wether they choose to or not) – that is, deciding to do nothing about a probable event.  Inaction is just as much as a choice as performing a specific action. Prescriptive analytics aims to provide the action steps necessary to achieve results of predictive analytics and how each action will  impacts everything else.

Three Phases of Analytics


A simple way of viewing the phases of business analytics is to compare it to healthcare.

Before deciding to visit a doctor, there are typically symptoms experienced by an individual that can be readily described (e.g. headache, fatigue, pain, etc.) – in other words this is raw data. At this point a doctor can interpret symptoms and/or run additional tests to ultimately make a diagnosis, he is only telling you what disease or ailment that you have. This is Descriptive Analytics.

The next step a doctor can do is to analyze the situation further. From the data obtained from the additional tests or the severity of the symptoms a doctor can make a prognosis – that is a forecast of the most likely outcome of the diagnosed disease or ailment. This is Predictive Analytics.

Lastly, a doctor may be able to explain the possible treatments of the disease or ailment. The treatments may have varying success probabilities but may also have possible side effects. Choosing a treatment will have defined benefits such as treating symptoms – but can also introduce additional factors not previously seen before. This is Prescriptive Analytics.

The previous example is pretty rudimentary, but it demonstrates an important point.  The reason why the patient was able to identify and take action on a perceived problem (symptoms) was by the seeking help of a medical professional who is trained in diagnosing and treating diseases. The patient in this case can be easily compared to any business professional. Analytics professionals can assist businesses identify and take actions on perceived problems, but the outcome relies heavily on the available data.



Business Analytics (Wikipedia)

List of 6 Analytics Maturity Models

A Maturity Model is a tool to assess your organization’s process capability in a specific domain – it is typically divided into levels or stages. The idea is that you cannot move to a higher stage until you have comprehensively met the requirements of all stages below. The goal is to achieve the highest step.

The idea of a Maturity Model is nothing new. One of the earliest maturity models developed, was in conjunction with the U.S. Department of Defense: the Capability Maturity Model, which focused on improving the software development process. The CMM is inspired by the ideas  found in the book Managing the Software Process (Humphrey).  Carnegie Mellon University now administers and markets CMMi (Capability Maturity Model Integration) – a process improvement training and appraisal program.

The Five CMM Levels: Initial -> Managed -> Defined -> Quantitatively Managed -> Optimizing

I first came across the concept of an Analytics Maturity Model when reading Competing on Analytics: The New Science of Winning (Davenport, Harris).

Analytics Maturity Pyramid
Figure 1: Analytics Maturity Pyramid

The model introduced has also appeared in a step-wise notation with definitions at each stage (Figure 1).

Five Stages of Analytical Maturity
Figure 2: Five Stages of Analytical Maturity

This model was developed by the analytics software developer SAS who wrote a white paper on the model.  Similar to CMM, it also has five levels (Figure 2).

Many other organizations have started to offer their own analytics maturity models, each with their own spin. Some offer access to a self-assessment tool, where you can fill out certain information about your company and proceed to be evaluated. Here is a list of five others (in no particular order).

1.  Online Analytics Maturity Model (OAMM) – Cardinal Path

Cardinal Path’s Online Analytics Maturity Model measures your organizations analytics maturity against six areas: Governance, Objectives, Scope, Team & Expertise, Improvement Process Methodology and Tools, Technology & Data Integration. The OAMM is presented in the style of a radar graph indicating a score in each of the six areas (Figure 3).

Cardinal Path's Online Analytics Maturity Model
Figure 3: Cardinal Path’s Online Analytics Maturity Model

2. Adobe Analytics Maturity Model – Adobe

Adobe’s Analytics Maturity Model is focused around their Marketing Cloud product suite and is primarily directed towards web analytics (Figure 4).

Adobe Web Analytics Maturity Model
Figure 4: Adobe Web Analytics Maturity Model

3. Big Data & Analytics Maturity Model – IBM

IBM’s Big Data & Analytics Maturity Model is also a five level model that focuses not only on analytics maturity, but also other areas of the business including: business strategy, information, culture and execution, architecture and governance (Figure 5).

IBM Big Data & Analytics Maturity Model
Figure 5: IBM Big Data & Analytics Maturity Model

4. Data Science Maturity Model – Booz Allen Hamilton

Booz Allen Hamilton’s maturity model is heavily focused on data science – the process by which insight is gained through data (Figure 6).

Booz Allen Hamilton Data Science Maturity Model
Figure 6: Booz Allen Hamilton Data Science Maturity Model

5. Informs Analytics Maturity Model (AMM) – Informs

The organization behind the Certified Analytics Professional program has developed their own maturity model that is quite different from the list above.

Compared to the other models that evaluate your organization’s analytical maturity as a whole (which Informs also does – Figure 7) – it evaluates the maturity of the following categories and factors:

  1. Organization Maturity (Figure 8)
    1. People
    2. Leadership Impact
    3. Measures
    4. Processes
  2. Analytics Capability Maturity
    1. Analytic Framework
    2. Roles and Skills
    3. Analytic Services
    4. Analytic Processes
  3. Data and Infrastructure Maturity to Support Analytics
    1. Health
    2. Access
    3. Traceability
    4. Analytics Architecture
Informs Assessment Summary Score
Figure 7: Informs Assessment Summary Score
Informs Organization Maturity Graph
Figure 8: Informs Organization Maturity Graph

You have seen six different approaches to evaluating your organizations analytic maturity – some take a global view of your organization and place you along a scale, others evaluate you on a more detail level and roll up your results into a final score.

Do you prefer one model over another? Are there other models out there  that you think should have made this list? Please share your responses in the comments below.


What Topics does CAP® Cover?

BrightTalk has a series of recorded Webinars that cover all of the domains on the CAP® Certification Exam. These are presented by CAP® Certified professionals and members of the CAP® Certification board. These webinar do not teach you specific topics on the CAP® Exam, but rather explain the areas on which you will be tested.

Note: To view these webinars you will need to signup for a free account with BrightTalk.

CAP® Webinar Training Series Part I

Presented by: Scott Nestler (U.S. Army), K. Matthew Windham, CAP® and Director-Analytics at NTEL-X

Summary: Explains the history of Analytics, development of the CAP® Certification, and preparation strategy.


CAP® Webinar Training Series Part II

Presented by: Frank Stein, CAP®, Director, Analytics Solution Center for IBM’s Washington Office

Summary: Explains the first two out of seven domain in the CAP® examination: Business Problem Framing and Analytics Problem Framing.


CAP® Webinar Training Series Part III

Presented by: Robert F. Bordley, CAP®, Booz-Allen-Hamilton’s Troy, MI office

Summary: Explains the third domain in the CAP® examination: Data.


CAP® Webinar Training Series Part IV

Presented by: Subhashish Samaddar, PhD, CAP®, Director MS in Analytics, Georgia State University

Summary: Explains the fourth domain in the CAP® examination: Methodology (Approach) Selection.


CAP® Webinar Training Series Part V

Presented by: Alan Taber, CAP®, Lockheed Martin

Summary: Explains the final three domains in the CAP® examination: Model Building, Deployment and Model Lifecycle Maintenance.


Watching these webinars should give you a comprehensive overview of the CAP® Certification process. If you are looking for specific information and tutorials on the subject matter tested by the CAP® exam – stay tuned to this blog. I will be publishing posts on all the areas tested by the CAP® exam.

What does CAP® Certification cost?

CAP Logo

Most people wonder, “What does the CAP® Certification cost?”

As of February 28, 2016 – the CAP® exam fee varies based upon membership in INFORMS which carries its own membership fee of $158 for Regular membership.

After your 3rd year of CAP® certification, there is a required annual maintenance fee.

There is a discounted reexamination fee if the exam is attempted a 2nd or 3rd time within the first year of applying.

Non-Informs Member Fees

Exam Fee: $695
Annual Maintenance Fee: $100
Reexamination Fee: $400

Informs Member Fees

Exam Fee: $495
Annual Maintenance Fee: $100
Reexamination Fee: $300

Other General Fees

Hand-Scoring Fee: $75
Processing Fee on Approved Refunds: $100
Appeals Processing Fee: $150

INFORMs offers a reduced Group Rate for 10 or more applicants.

What is CAP®?

CAP® is an acronym for Certified Analytics Professional.

The Institute for Operations Research and the Management Sciences (INFORMS) developed the CAP® Program in 2011 – 2012 as way to certify individuals in the area of analytics. The CAP Program is very similar to the Project Management Professional (PMP) certification developed by the Project Management Institute.

INFORMS defines analytics as the scientific process of transforming data into insight for making better decisions.

Knowledge Domains

The CAP® Program covers seven domains of knowledge:

  1. Business Problem (Question) Framing
  2. Analytics Problem Framing
  3. Data
  4. Methodology (Approach) Selection
  5. Model Building
  6. Deployment
  7. Model Life Cycle Management

Education Requirements

The CAP® Program requires the candidate to have a Bachelors or Masters degree from a regionally accredited college in an analytics-related area such as: analytics, operations research, management science, statistics, engineering, business, theoretical or applied mathematics, information technology, computer science, or decision science.

The INFORMS Analytics Certification Board may consider additional degrees as appropriate and may waive the educational requirement on a case by case basis.

The candidate will be required to submit a an official transcript as part of the application process.

Experience Requirements

Depending on the degree held by the candidate, there are varying years of experience required for application.

  • Masters (MA/MS) in an analytics-related area: 3 years.
  • Bachelors (BA/BS) in an analytics-related area: 5 years.
  • Bachelors (BA/BS) in a non-analytics-related area: 7 years.

Candidates will be expected to provide detailed information about their work experience including: employer name, immediate supervisor, contact information, and dates of employment.


This post is intended to be a high-level overview of the CAP® Program. In the posts to follow, I will discuss the application process, the examination, fees and the renewal process.

Visit the Certified Analytics Professional Program website for additional information.