FDA notes - CCA 1

UNIT 1 – DATA ANALYTICS

1. Introduction to Data Analytics
In today’s information era, massive volumes of data are being generated
through business processes, social media, IoT devices, healthcare systems,
finance, etc. Extracting valuable knowledge from this raw data for decision-
making is the purpose of Data Analytics. It is the complete process that
involves collecting, cleaning, processing, exploring, and interpreting data to
convert it into actionable insights. It bridges the gap between raw information
and intelligent decisions.

2. Need for Data Analytics

● Helps organisations make better decisions
● Converts past data into future strategies
● Optimizes operational efficiency
● Predicts risks, failures & customer demands
● Supports innovation, personalization & revenue growth

3. Types of Data Analytics

(i) Descriptive Analytics

Focus: Understand past events
Question: “What happened?”
Example: Last month’s sales chart
Features:
● Reports, dashboards, KPIs
● Averages, sums, counts
Use: Understanding trends and patterns.

(ii) Diagnostic Analytics

Focus: Causes of past events
Question: “Why did it happen?”
Example: Why did profits decrease in Q2?
Features:
● Drill-down analysis
● Correlation & data mining
Use: Root-cause investigation.

(iii) Predictive Analytics

Focus: Future trends & forecasting
Question: “What is likely to happen next?”
Example: Predicting customer churn rate
Techniques: ML, regression, time-series
Use: Forecasting sales, demand, risks.
(iv) Prescriptive Analytics
Focus: Recommendations & actions
Question: “What should we do?”
Example: Suggesting optimal pricing strategy
Techniques: AI, optimization, simulations
Use: Automated decision systems.

4. Applications of Data Analytics

● Business: Customer segmentation, recommendation engines
● Healthcare: Disease prediction, clinical decision support
● Finance: Fraud detection, algorithmic trading
● Manufacturing: Predictive maintenance for machines
● Retail: Inventory optimization, demand prediction
● Government: Smart cities, citizen behaviour analysis

5. Benefits of Data Analytics

● Improved strategic decision-making
● Higher efficiency & cost-savings
● Increased customer satisfaction
● Boosts revenue, innovation & competitiveness
● Detects risks/frauds at an early stage

6. Roles in Data Analytics

(a) Data Analyst
Works on structured data to interpret, visualise, and report trends.
Skills required:
● Excel, SQL, Python
● Tableau/PowerBI
● Communication & problem-solving
(b) Data Scientist
Creates predictive models using machine learning on large & complex datasets.
Skills required:
● Python/R, ML, statistics
● Big data tools (Hadoop/Spark)
● Domain expertise

7. Difference Between Data Analytics & Data Analysis

Point Data Analysis Data Analytics
Scope Narrow (examines Broad (end-to-end
data) process)
Objective Understand patterns/ Drive decisions &
insights strategies
Components Cleaning, exploration Acquisition → Cleaning
→ Modelling →
Deployment
 data) process)
Objective Understand patterns/ Drive decisions &
insights strategies
Components Cleaning, exploration Acquisition → Cleaning
→ Modelling →
Deployment
Usage Part of analytics Complete discipline
process

8. Data Analytics Life Cycle (BONUS POINT)

. Data Identification & Collection
. Data Cleaning & Pre-processing
. Data Exploration & Analysis
. Modelling & Algorithm building
. Interpretation of Results
. Deployment & Monitoring

EXAM-STYLE QUESTION & ANSWERS

Q1. What is Data Analytics?

Ans: Data Analytics is the scientific process of collecting, transforming,
examining and interpreting raw data to discover useful information that
supports decision-making and problem solving.

Q2. Explain the four types of Data Analytics.

Ans:
● Descriptive – summarises past data
● Diagnostic – investigates causes
● Predictive – forecasts future events using ML
● Prescriptive – recommends optimal actions

Q3. Mention any four applications of Data Analytics.

Ans: Healthcare (disease prediction), Finance (fraud detection), Retail (demand
forecasting), Manufacturing (preventive maintenance).

Q4. Explain difference between Data Scientist & Data Analyst.

Ans: Data Analysts focus on interpreting structured data using statistical tools,
whereas Data Scientists build machine learning models on large & complex
data for predictive analysis.

Q5. List any four advantages of Data Analytics.

Ans:
. Helps in informed decision-making
. Optimises operational performance
. Detects risks/frauds early
. Enhances customer experience
UNIT-2 – DEALING WITH DIFFERENT TYPES OF DATA
1. Introduction
Different real-world scenarios produce different kinds of data. A Data Analyst
must not only understand what type of data they are working with, but also
know how to handle, store, process, and analyse each type effectively —
because the tools, techniques and challenges differ for every category.

1. Roles in the Analytics Ecosystem

In a modern data-driven organisation, multiple professionals work together to

transform raw data into meaningful business decisions. Although their work
may overlap, each role has a different area of focus, responsibilities and skill-
set.

(A) Data Analyst

They work mostly with structured data stored in spreadsheets, SQL tables, etc.
Their role is to extract meaningful trends, prepare reports and help
management understand historical or present data.

Responsibilities:
• Collect, clean and prepare data
• Use SQL queries, Excel formulas, Python scripts
• Create charts and dashboards (PowerBI/Tableau)
• Present findings in an easy-to-understand manner

Focus: “What is the data saying right now?”

(B) Data Scientist

They handle large and complex datasets and use statistical and machine
learning models to make forecasts or discover deeper patterns. Their job is
high-level predictive and prescriptive modelling.

Responsibilities:
• Build prediction & classification models
• Use advanced tools: Python/R, TensorFlow, PyTorch
• Perform feature engineering & algorithm tuning
• Communicate insights with stakeholders

Focus: “What will happen next and what should be done?”

(C) Business Analyst (BA)

This role acts as a bridge between technical teams and business stakeholders.
A BA understands organisational problems and identifies how data-backed
solutions can help.

Responsibilities:
• Gather business & user requirements
• Develop use-cases and documentation
• Suggest improvements in processes
• Translate business needs into data projects

Focus: “How do we solve the business problem using data?”

(D) Business Intelligence (BI) Analyst

The BI Analyst specialises in creating visual dashboards and transforming raw

numbers in databases into decision-friendly representations for leadership.

Responsibilities:
• Extract data from warehouses
• Build slick dashboards (Tableau, PowerBI, Qlik)
• Track KPIs and create automated reports
• Assist in executive strategic decision making

Focus: “How can data be visualised for faster decision-making?”

2. Types of Analytics (Extended Explanation)

The field of analytics has progressed in stages — each stage answers a

different kind of question and provides increasing business value.

(i) Descriptive Analytics

It simply describes what has already happened using statistical summaries

and visualisation. This is the starting point of any analytics journey.

Example: “Total sales last year = ₹50 Cr”

Key Points:
• Uses counts, percentages, mean, graphs
• Helps identify trends & patterns
• Easy, fast, but offers limited actionability
(ii) Diagnostic Analytics

This digs deeper to find the reasons behind events. It helps management
understand the factors that caused particular outcomes.

Example: “Sales dropped because online ads were stopped.”

Techniques Used:
• Drill-down, correlation, comparison, data mining

(iii) Predictive Analytics

Uses historical data to forecast future outcomes with the help of statistical
and machine-learning models.

Example: “Predicted customer churn next month is 12%”

Tools & Techniques:

• Regression, classification, time-series, ML libraries
• Needs large datasets and model training

(iv) Prescriptive Analytics

This is the most advanced form — it not only predicts what will happen, but
also recommends what action should be taken for the best results.

Example: “Increase Instagram ads by 20% to boost sales.”

Techniques Used:
• Optimization, simulation, reinforcement learning
• Powers intelligent decision systems (recommender systems,
chatbots, etc.)