[Analysis] Types of Data Analytics – Descriptive | Diagnostic | Predictive | Prescriptive

  • Blog|FEMA & Banking|
  • 7 Min Read

Descriptive, diagnostic, predictive and prescriptive analytics explained from IIBF’s Emerging Technologies courseware, with techniques, banking examples and how the four fit together.

  • By Taxmann
  • |
  • Last Updated on 14 November, 2026

Types of Data Analytics

There are four types of data analytics: descriptive, diagnostic, predictive and prescriptive. Descriptive analytics explains what happened, diagnostic analytics why it happened, predictive analytics what is likely to happen, and prescriptive analytics what should be done. The IIBF courseware on Emerging Technologies frames each type with a banking question, from whether the number of frauds has gone down to what action can reduce loan delinquency in a sector. Value and complexity both rise as an organisation moves from descriptive to prescriptive analytics.

Table of Contents

  1. What is data analytics?
  2. What are the four types of data analytics?
  3. What is descriptive analytics?
  4. What is diagnostic analytics?
  5. What is predictive analytics?
  6. What is prescriptive analytics?
  7. How do the four types fit together?
  8. How do banks use data analytics?
  9. Quick answers

1. What is data analytics?

Data analytics is the process and technology of analysing raw data to draw meaningful conclusions from it. Its techniques are automated into processes and algorithms that work over raw data, and they can reveal hidden trends and metrics that would otherwise be lost in huge data sets. Businesses use the results to optimise processes and work more efficiently.

Banks use data analytics to make better business decisions and to analyse customer trends and satisfaction, which leads to customer-centric products and services. It also gives predictive insights, so that an organisation can anticipate future trends and make strategic decisions in advance.

A typical analysis starts by understanding what data is needed and how it is grouped, for example by age, income or gender. The data is then gathered, organised in a spreadsheet, database or other software, and cleaned to remove duplication, errors and gaps before it reaches the analyst. Methodologies are also classed as exploratory data analysis (EDA), which looks for patterns and relationships in data, and confirmatory data analysis (CDA), which tests whether hypotheses about a data set are true or false.

2. What are the four types of data analytics?

There are four basic types of data analytics: descriptive, diagnostic, predictive and prescriptive. Each answers a different question, and the courseware gives an example for each, most of them from banking.

Type Question it answers What it does Banking example
Descriptive “What happened?” Explains what has happened over a given period, using historical data Whether the recovery rate has gone up or the number of frauds has gone down
Diagnostic “Why did it happen?” Investigates the reasons behind a result, with more diverse data and some hypothesising Why spending on marketing a product has not improved the business
Predictive “What is likely to happen?” Forecasts the near future from data, using models What happens to growth when the lending rate for a particular sector is reduced, and what the profit will be under given conditions
Prescriptive “What should be done?” Suggests a course of action What action is required when the delinquency of loans in a particular zone or sector is higher

Taxmann.com | Research | Subscribe Now!

3. What is descriptive analytics?

Descriptive analytics describes what has already happened in a business. Historical data is collected, organised and presented so that stakeholders can understand it easily, usually through graphs, charts, reports and dashboards. It does not draw inferences or make predictions; it is the starting point that prepares data for further analysis.

It relies on two methods: data aggregation, which collects and organises data into manageable data sets, and data mining, which finds the patterns, trends and meanings in them. The maths is simple, mostly arithmetic, averages and per cent changes. Typical measures include year-over-year growth of business mix and profits, month-over-month sales increases, user counts and total revenue per subscriber.

The process runs in four steps: setting business metrics to track performance against objectives, collecting and cleansing the data, analysing it with summary statistics, clustering, pattern tracking and regression analysis, and presenting the findings in charts and graphs for people who are not analysts. Descriptive analytics fits easily into day-to-day operations and needs no analytics expertise, but it does not see past the surface of the data.

4. What is diagnostic analytics?

Diagnostic analytics answers the question “Why did it happen?” It is a form of advanced analytics that takes descriptive analytics a step further, from recording the facts to uncovering the reasons behind a result.

Its techniques are data discovery, drill-down, data mining and correlations. In discovery, analysts identify the data sources that will help them interpret the results. Drilling down means focusing on one facet of the data. Data mining automatically extracts information from a massive set of raw data, and consistent correlations help pin down the parameters of the investigation. Analysts often have to look beyond the company’s own data and pull in external sources to find correlations and determine causality.

5. What is predictive analytics?

Predictive analytics uses data to answer the question “What is likely to happen?” An organisation that clearly understands what has happened in its business can move on to this level. Its techniques include regression analysis, forecasting, multivariate statistics, pattern matching and predictive modelling.

Three predictive models are in common use:

  • Decision trees place data into sections based on variables such as price or market capitalisation. Branches show the choices available and leaves show particular decisions. They are the simplest models, easy to understand and useful when a decision is needed quickly.
  • Regression is the model used most in statistical analysis. It works out a formula for the relationship between the inputs, for example how price and other key factors shape the performance of a security.
  • Neural networks imitate how the human brain works and use artificial intelligence and pattern recognition to handle complex data relationships, especially when there is too much data or no formula linking inputs and outputs.

Predictive analytics is more challenging to implement. It needs a large volume of high-quality data and a thorough knowledge of statistics and programming languages such as R or Python, skills that many firms may lack in-house. It is also one of the common uses of supervised machine learning.

6. What is prescriptive analytics?

Prescriptive analytics works out what should be done to reach a goal. It is a subset of advanced analytics that examines data to answer “What should be done?” or “How can we make our goals a reality?”, using techniques such as graph analysis, simulation, complex event processing, neural networks, recommendation engines, heuristics and machine learning.

It is the highest and most advanced level of analytics, and the hardest to attain. How well it works depends on how well the business has completed each earlier stage of analytics. Its value lies in letting an organisation decide on the basis of carefully studied data rather than gut instinct, which makes the desired outcome, such as revenue growth, more likely.

7. How do the four types fit together?

They build on one another. The courseware’s chart sets the four types against the value they add and the complexity of putting them in place, and its advice is to begin with descriptive analytics, the easiest to implement, before moving through diagnostic and predictive to prescriptive analytics.

Looks at Types Purpose
The past Descriptive and diagnostic Explain what happened and why
The future Predictive and prescriptive Use historical data to predict what will happen and what actions can influence the outcome

Used together, the four tell one story: what the organisation has, what it needs and what it can achieve. Predictive and prescriptive analytics are impossible without the right foundations, so the progression matters.

8. How do banks use data analytics?

Banks and other financial services firms have turned big data into a competitive advantage, from capturing new market opportunities to cutting fraud. The uses described in the IIBF courseware include:

  • Fraud detection and compliance. Analysing massive volumes of transaction data, together with interaction events and customer behaviour, reveals patterns that signal fraud and speeds up regulatory reporting. Banks and credit card companies also analyse withdrawal and spending patterns to prevent fraud and identity theft.
  • Money laundering prevention. Banks must show due diligence and file suspicious activity reports. Analysing massive volumes of structured and unstructured transaction data helps identify complex AML transactions, and graph analytics shows linkages that were unknown before.
  • Regulatory and compliance analysis, where firms must assemble large amounts of data and build complex risk models quickly.
  • Targeted marketing, predicting customer preferences and advertising to interested people.
  • Customer lifetime value, identifying the bank’s most valuable customers from their activity and purchasing patterns, so that marketing, sales and customer support can focus on them and the bank can increase its wallet share.
  • Innovation, where a clearer view of market trends and client needs leads to better decisions on new products and services.

Much of this runs on big data platforms; our post on the Hadoop ecosystem shows how banks store and process data at that scale.

9. Quick answers

What are the four types of data analytics?

Descriptive, diagnostic, predictive and prescriptive analytics. They answer, in turn, what happened, why it happened, what is likely to happen and what should be done.

What is descriptive analytics?

Descriptive analytics explains what has already happened in a business, using historical data presented through graphs, charts, reports and dashboards. It does not draw inferences or make predictions.

What is diagnostic analytics?

Diagnostic analytics answers “Why did it happen?” It uses data discovery, drill-down, data mining and correlations to uncover the reasons behind a result.

What is predictive analytics?

Predictive analytics uses data to answer “What is likely to happen?” Its common models are decision trees, regression and neural networks, and it needs a large volume of high-quality data.

What is prescriptive analytics?

Prescriptive analytics works out what should be done to reach a goal, using techniques such as simulation, graph analysis, recommendation engines, heuristics and machine learning. It is the most advanced level of analytics.

What is the difference between descriptive and predictive analytics?

Descriptive analytics looks at the past and explains what happened. Predictive analytics uses historical data to forecast what is likely to happen in the future.

Which type of data analytics is the most advanced?

Prescriptive analytics. It is the highest degree of analytics, the most advanced level and the hardest to attain, and it depends on how well the earlier stages have been completed.

How is data analytics used in banking?

Banks use data analytics for fraud detection and compliance, money laundering prevention, regulatory analysis, targeted marketing and customer lifetime value, among other uses.


Chapter 1 of Emerging Technologies (2026 Edition), the Indian Institute of Banking & Finance’s courseware for its Certificate Course on Emerging Technologies, published by Taxmann, opens Module A: Introduction to Data Analytics. It covers data analytics and its four types, summarisation and interpretation, data visualisation, data analytics tools and the use of data analytics in banking, and ends with multiple choice questions and terminal questions for practice.

For the rules that banks work under, Taxmann.com | Research, FEMA & Banking brings together the Acts, Rules, circulars and notifications, case laws and articles on FEMA, banking and insurance. Taxmann.com | Store also lists IIBF’s courseware for its other certificate courses, including Information System for Banks and IT Security.

Related reading: data summarisation and visualisation strategies · the role of big data analytics in chartered accountancy.

More in this series: emerging technologies in banking · structured and unstructured data · types of machine learning · the Hadoop ecosystem · characteristics of big data.

Based on the 2026 Edition of Emerging Technologies, IIBF’s courseware for the Certificate Course on Emerging Technologies.

Disclaimer: The content/information published on the website is only for general information of the user and shall not be construed as legal advice. While the Taxmann has exercised reasonable efforts to ensure the veracity of information/content published, Taxmann shall be under no liability in any manner whatsoever for incorrect information, if any.

Leave a Reply

Your email address will not be published. Required fields are marked *

Everything on Tax and Corporate Laws of India

To subscribe to our weekly newsletter please log in/register on Taxmann.com

Author: Taxmann

Taxmann Publications has a dedicated in-house Research & Editorial Team. This team consists of a team of Chartered Accountants, Company Secretaries, and Lawyers. This team works under the guidance and supervision of editor-in-chief Mr Rakesh Bhargava.

The Research and Editorial Team is responsible for developing reliable and accurate content for the readers. The team follows the six-sigma approach to achieve the benchmark of zero error in its publications and research platforms. The team ensures that the following publication guidelines are thoroughly followed while developing the content:

  • The statutory material is obtained only from the authorized and reliable sources
  • All the latest developments in the judicial and legislative fields are covered
  • Prepare the analytical write-ups on current, controversial, and important issues to help the readers to understand the concept and its implications
  • Every content published by Taxmann is complete, accurate and lucid
  • All evidence-based statements are supported with proper reference to Section, Circular No., Notification No. or citations
  • The golden rules of grammar, style and consistency are thoroughly followed
  • Font and size that's easy to read and remain consistent across all imprint and digital publications are applied