Big Data Analytics
Class 12 · Artificial Intelligence
5.5 Big Data Analytics
Big Data Analytics is the process of using advanced analytical techniques to examine extremely large and diverse datasets. These datasets may contain structured, semi-structured and unstructured data and may range from terabytes to zettabytes in size.
The primary purpose of Big Data Analytics is to discover patterns, identify trends, uncover useful information and address complex challenges. Organisations use these insights to improve processes, support decision-making and make better predictions.
Big Data Analytics converts large and complex datasets into meaningful insights that can support decision-making and problem-solving.
Why is Big Data Analytics Important?
Modern organisations generate enormous amounts of data from websites, mobile devices, online transactions, social networking platforms, sensors and other digital systems. Simply collecting this data is not sufficient.
Big Data Analytics helps organisations analyse this information to identify patterns, trends and relationships that may not be visible through traditional methods.
- Helps in making data-driven decisions.
- Helps organisations identify trends and patterns.
- Supports prediction and forecasting.
- Helps improve business processes and efficiency.
- Helps organisations understand customers and their behaviour.
- Supports innovation and the development of better products and services.
Types of Big Data Analytics
Big Data Analytics is commonly divided into four major types: Descriptive, Diagnostic, Predictive and Prescriptive Analytics.
| Type of Analytics | Main Question | Purpose |
|---|---|---|
| Descriptive Analytics | What happened? | Analyses past and present data to understand what has already happened. |
| Diagnostic Analytics | Why did it happen? | Examines data to identify the reasons or causes behind an event or outcome. |
| Predictive Analytics | What is likely to happen? | Uses historical data, patterns and models to forecast possible future outcomes. |
| Prescriptive Analytics | What should we do? | Suggests suitable actions or decisions to achieve a desired outcome. |
1. Descriptive Analytics
Descriptive Analytics focuses on understanding what has already happened by analysing historical and current data.
It summarises data in a meaningful form using reports, dashboards, charts and other visualisations.
A school analyses the previous month's attendance records to determine the average attendance of students in each class.
Descriptive Analytics = What happened?
2. Diagnostic Analytics
Diagnostic Analytics focuses on finding out why something happened. It examines data to identify relationships, patterns and possible causes.
If a school's attendance rate suddenly decreases, diagnostic analytics can be used to investigate possible reasons, such as examination schedules, weather conditions or other relevant factors.
Diagnostic Analytics = Why did it happen?
3. Predictive Analytics
Predictive Analytics uses historical data, patterns and analytical or machine learning models to estimate what may happen in the future.
Predictions are based on available data and therefore represent likely outcomes rather than guaranteed results.
A factory can analyse historical temperature and vibration data from machines to predict whether a machine is likely to fail in the future.
Predictive Analytics = What will happen?
4. Prescriptive Analytics
Prescriptive Analytics goes beyond predicting future outcomes. It recommends suitable actions that can help achieve a desired result.
A food delivery service analyses traffic conditions, customer locations and available delivery personnel to determine the most efficient delivery routes.
Prescriptive Analytics = What should we do?
Comparison of the Four Types of Analytics
| Type | Question | Focus |
|---|---|---|
| Descriptive | What happened? | Past and present |
| Diagnostic | Why did it happen? | Causes and reasons |
| Predictive | What will happen? | Future possibilities |
| Prescriptive | What should we do? | Recommended actions |
Global Trends Driving Big Data Analytics
The growth of Big Data Analytics has been supported by several important technological and social developments. The major global trends include Moore's Law, Mobile Computing, Social Networking and Cloud Computing.
1. Moore's Law
Moore's Law describes the continuing growth in computing power over time. Increasing computing capabilities have made it possible to store and analyse increasingly large volumes of data.
Increasing computing power makes it easier to process and analyse large datasets.
2. Mobile Computing
The widespread use of smartphones, tablets and other mobile devices has resulted in continuous data generation and collection.
Mobile computing enables users to remain connected and allows organisations to collect data from different locations in real time.
3. Social Networking
Social networking platforms generate enormous amounts of data through user interactions, posts, comments, images, videos, likes and other activities.
Analysing this information can help organisations understand user behaviour, interests and trends.
4. Cloud Computing
Cloud Computing provides access to computing resources such as storage, processing power, hardware and software through the internet.
Organisations can use cloud resources without making large investments in their own physical infrastructure. Many cloud services follow a pay-as-you-go model.
| Global Trend | Contribution to Big Data Analytics |
|---|---|
| Moore's Law | Increasing computing power supports the processing of large datasets. |
| Mobile Computing | Enables continuous connectivity and data generation through mobile devices. |
| Social Networking | Generates massive amounts of user-generated data and interactions. |
| Cloud Computing | Provides scalable storage and computing resources over the internet. |
Big Data Analytics in Education
Big Data Analytics can also be applied in the education sector. Schools and educational institutions generate data through attendance systems, examinations, learning management systems, ERP systems and online learning platforms.
A school can analyse examination results, attendance and academic performance to identify learning patterns and support data-driven academic planning.
Activity
Consider an online learning platform that records student attendance, test scores, assignment submissions and learning activities.
Identify which type of analytics would be appropriate in each situation:
- Finding the average marks obtained by students.
- Finding the reason for a decline in student performance.
- Predicting which students may require additional academic support.
- Recommending the most suitable learning intervention for students.
Click to View Answer
- Descriptive Analytics
- Diagnostic Analytics
- Predictive Analytics
- Prescriptive Analytics
Competency-Based Question
A food delivery company collects information about orders, customer locations, delivery times and traffic conditions. The company wants to analyse past delivery performance, identify reasons for delays, predict future delivery times and recommend the best delivery routes.
Identify the type of analytics applicable to each requirement.
Click to View Answer
- Analysing past delivery performance → Descriptive Analytics
- Finding reasons for delivery delays → Diagnostic Analytics
- Predicting future delivery times → Predictive Analytics
- Recommending the best delivery routes → Prescriptive Analytics
Think Like a Data Analyst
A school wants to use its historical examination data to identify students who may require additional support in the next examination.
Which type of Big Data Analytics would be most appropriate? Explain your answer.
Click to View Answer
Predictive Analytics would be appropriate because historical examination data can be analysed to identify patterns and estimate which students may require additional academic support in the future.
Common Beginner Mistakes
- Confusing Descriptive Analytics with Predictive Analytics.
- Remembering only the four names without understanding the questions answered by each type.
- Thinking that Predictive Analytics guarantees the future outcome. It only provides a likely prediction based on available data.
- Confusing Diagnostic Analytics with Prescriptive Analytics.
- Forgetting that Prescriptive Analytics recommends an action rather than simply predicting an outcome.
- Confusing Cloud Computing with a physical data storage device. Cloud Computing provides computing resources and services over the internet.
- Forgetting that Moore's Law is associated with the growth of computing power.
Quick Revision
- Big Data Analytics analyses extremely large and diverse datasets to discover useful patterns, trends and insights.
- Descriptive Analytics → What happened?
- Diagnostic Analytics → Why did it happen?
- Predictive Analytics → What will happen?
- Prescriptive Analytics → What should we do?
- Moore's Law → Growth in computing power.
- Mobile Computing → Continuous connectivity and data generation.
- Social Networking → Massive user-generated data.
- Cloud Computing → Scalable computing and storage resources through the internet.
Memory Trick
Remember the four types of analytics using:
What → Why → What Next → What To Do
- What happened? → Descriptive
- Why did it happen? → Diagnostic
- What will happen? → Predictive
- What should we do? → Prescriptive
Exam Tips
- Learn the four types of analytics along with their corresponding questions.
- Descriptive describes past or present events.
- Diagnostic identifies reasons or causes.
- Predictive forecasts likely future outcomes.
- Prescriptive recommends suitable actions.
- Remember the four global trends: Moore's Law, Mobile Computing, Social Networking and Cloud Computing.
- For competency-based questions, look for keywords such as past, reason, future prediction and recommendation/action.
Frequently Asked Questions (FAQs)
1. What is Big Data Analytics?
Big Data Analytics is the process of using advanced analytical techniques to analyse extremely large and diverse datasets to uncover patterns, trends and useful insights.
2. What are the four types of Big Data Analytics?
The four types are Descriptive, Diagnostic, Predictive and Prescriptive Analytics.
3. Which type of analytics answers "What happened?"?
Descriptive Analytics.
4. Which type of analytics answers "Why did it happen?"?
Diagnostic Analytics.
5. Which type of analytics is used to forecast future outcomes?
Predictive Analytics.
6. Which type of analytics recommends an action?
Prescriptive Analytics.
7. What are the major global trends driving Big Data Analytics?
The major trends are Moore's Law, Mobile Computing, Social Networking and Cloud Computing.
8. What is the role of Moore's Law in Big Data Analytics?
The increasing availability of computing power makes it easier to store, process and analyse increasingly large datasets.
9. How does Cloud Computing support Big Data Analytics?
Cloud Computing provides scalable computing, storage, hardware and software resources over the internet, often using a pay-as-you-go model.
10. How can Big Data Analytics be used in education?
It can be used to analyse attendance, examination results, learning activities and other educational data to identify patterns, support decision-making and improve academic planning.
Summary
- Big Data Analytics uses advanced analytical techniques to examine extremely large and diverse datasets.
- Its primary purpose is to uncover patterns, trends and useful insights.
- The four major types are Descriptive, Diagnostic, Predictive and Prescriptive Analytics.
- Descriptive Analytics answers: What happened?
- Diagnostic Analytics answers: Why did it happen?
- Predictive Analytics answers: What will happen?
- Prescriptive Analytics answers: What should we do?
- The major global trends driving Big Data Analytics are Moore's Law, Mobile Computing, Social Networking and Cloud Computing.
- Big Data Analytics can support better decision-making, forecasting, process improvement and innovation.
Next Topic: Working on Big Data Analytics