Data Analytics
1. Introduction
Data Analytics is the process of collecting, cleaning, transforming, analyzing, and interpreting data to discover useful information, patterns, and insights.
It helps organizations make better decisions based on data rather than assumptions.
Simple Definition
Data Analytics is the process of examining data to find useful patterns, trends, relationships, and insights that help in decision-making.
Example
A company has sales data containing:
| Product | City | Quantity | Sales |
|---|---|---|---|
| Laptop | Janakpur | 5 | 250000 |
| Mouse | Kathmandu | 20 | 20000 |
| Laptop | Birgunj | 3 | 150000 |
Using Data Analytics, we can find:
- Which product sells the most?
- Which city generates the highest sales?
- What is the total revenue?
- Which products are performing poorly?
- What sales trends exist?
2. Why Data Analytics is Important
Data Analytics is important because it helps organizations understand their data and make informed decisions.
Major benefits:
-
Better Decision-Making Helps businesses make decisions based on facts and evidence.
-
Identify Trends Finds patterns and changes in data.
-
Improve Business Performance Helps identify areas that need improvement.
-
Reduce Costs Finds unnecessary expenses and inefficient processes.
-
Understand Customers Helps understand customer behavior and preferences.
-
Increase Revenue Helps identify profitable products, customers, and markets.
-
Predict Future Trends Historical data can be used to estimate future outcomes.
-
Detect Problems Helps identify unusual transactions, errors, and fraud.
3. Data Analytics Process
The Data Analytics process generally follows these steps:
Data Collection ↓ Data Cleaning ↓ Data Preparation ↓ Data Exploration ↓ Data Analysis ↓ Data Visualization ↓ Interpretation ↓ Decision Making
Step 1: Data Collection
Data is collected from different sources.
Sources include:
- Databases
- Excel files
- CSV files
- Websites
- APIs
- Surveys
- Sensors
- Applications
- Social media
Step 2: Data Cleaning
Raw data may contain:
- Missing values
- Duplicate records
- Incorrect values
- Inconsistent formats
- Spelling errors
- Invalid data
Data cleaning removes or corrects these problems.
Example
Before cleaning:
Name Age Anuradha 21 Ram - Sita 20 Anuradha 21
After cleaning:
Name Age Anuradha 21 Sita 20
4. Data Preparation
Data preparation converts data into a suitable format for analysis.
It may include:
- Removing unnecessary columns
- Changing data types
- Handling missing values
- Converting categorical data
- Combining datasets
- Creating new columns
- Sorting and filtering data
5. Exploratory Data Analysis (EDA)
Exploratory Data Analysis is used to understand the structure and characteristics of a dataset.
EDA helps answer questions such as:
- What is the average value?
- What is the maximum value?
- What is the minimum value?
- Which category occurs most often?
- Are there unusual values?
- Are two variables related?
Common EDA techniques:
- Mean
- Median
- Mode
- Minimum
- Maximum
- Range
- Variance
- Standard deviation
- Correlation
- Histograms
- Bar charts
- Scatter plots
- Box plots
6. Data Analysis
Data analysis involves examining data to answer specific questions.
Example questions:
- What was the total sales?
- Which product had the highest sales?
- Which month had the highest revenue?
- Which city had the most customers?
- What percentage of customers returned?
7. Data Visualization
Data visualization represents data using graphical formats.
Common visualization types:
| Visualization | Purpose |
|---|---|
| Bar Chart | Compare categories |
| Line Chart | Show trends over time |
| Pie Chart | Show proportions |
| Histogram | Show distribution |
| Scatter Plot | Show relationships |
| Box Plot | Show spread and outliers |
| Heatmap | Show relationships using colors |
| KPI Card | Show important metrics |
Example
A sales dashboard might contain:
Total Sales: Rs. 500,000 Total Products: 25 Total Customers: 120 Average Sales: Rs. 4,167
8. Types of Data Analytics
There are four major types of Data Analytics.
8.1 Descriptive Analytics
Descriptive Analytics answers:
What happened?
It analyzes historical data to understand past events.
Example:
Total sales in September = Rs. 500,000
8.2 Diagnostic Analytics
Diagnostic Analytics answers:
Why did it happen?
It investigates the reasons behind an event.
Example:
Sales decreased because:
- Product prices increased
- Customer demand decreased
- Competitors offered discounts
8.3 Predictive Analytics
Predictive Analytics answers:
What is likely to happen?
It uses historical data, statistics, and machine learning to predict future outcomes.
Example:
Next month's expected sales = Rs. 600,000
8.4 Prescriptive Analytics
Prescriptive Analytics answers:
What should we do?
It recommends possible actions based on data and predictions.
Example:
Increase the stock of Laptop products because demand is expected to increase.
Four Types Summary
| Type | Main Question | Example |
|---|---|---|
| Descriptive | What happened? | Sales were Rs. 500,000 |
| Diagnostic | Why did it happen? | Sales decreased due to low demand |
| Predictive | What may happen? | Sales may increase next month |
| Prescriptive | What should we do? | Increase product stock |
9. Data Analytics Tools
Several tools are used for Data Analytics.
9.1 Microsoft Excel
Excel is commonly used for:
- Data cleaning
- Formulas
- Pivot Tables
- Charts
- Dashboards
- Basic statistical analysis
Common Excel functions:
SUM() AVERAGE() COUNT() MAX() MIN() IF() COUNTIF() SUMIF() VLOOKUP() XLOOKUP()
9.2 SQL
SQL is used to retrieve and analyze data stored in databases.
Example:
SELECT product, SUM(sales) FROM sales GROUP BY product;
This query calculates total sales for each product.
9.3 Python
Python is widely used for data analysis.
Popular Python libraries include:
- Pandas
- NumPy
- Matplotlib
- Seaborn
- SciPy
Example:
import pandas as pd data = pd.read_csv("sales.csv") print(data.head()) print(data["Sales"].sum()) print(data["Sales"].mean())
9.4 Power BI
Power BI is a business intelligence and data visualization tool.
It can be used to:
- Import data
- Clean data
- Create relationships
- Create charts
- Create dashboards
- Create KPI cards
- Generate reports
9.5 Tableau
Tableau is a data visualization and business intelligence tool.
It is commonly used to create:
- Interactive dashboards
- Charts
- Reports
- Data visualizations
10. Important Data Analytics Skills
A Data Analyst should develop the following skills:
Technical Skills
- Excel
- SQL
- Python
- Power BI
- Tableau
- Statistics
- Data Visualization
- Database knowledge
Analytical Skills
- Problem-solving
- Critical thinking
- Logical thinking
- Pattern recognition
- Statistical reasoning
Communication Skills
A Data Analyst should be able to explain:
- What the data shows
- Why the result is important
- What problems were identified
- What actions can be taken
11. Data Analytics Example
Suppose a company has the following sales data:
| Product | City | Quantity | Price | Total |
|---|---|---|---|---|
| Laptop | Janakpur | 2 | 50000 | 100000 |
| Mouse | Kathmandu | 10 | 1000 | 10000 |
| Laptop | Birgunj | 1 | 80000 | 80000 |
| Keyboard | Janakpur | 5 | 12000 | 60000 |
A Data Analyst can calculate:
Total Sales
100000 + 10000 + 80000 + 60000 = 250000
Therefore:
Total Sales = Rs. 250,000
Total Quantity
2 + 10 + 1 + 5 = 18
Therefore:
Total Quantity = 18
Highest Sales
Laptop = Rs. 100,000
Therefore, the Laptop entry in this dataset has the highest sales value.
12. Data Analytics Using Python
Example Dataset
import pandas as pd data = { "Product": ["Laptop", "Mouse", "Laptop", "Keyboard"], "City": ["Janakpur", "Kathmandu", "Birgunj", "Janakpur"], "Quantity": [2, 10, 1, 5], "Price": [50000, 1000, 80000, 12000], "Total": [100000, 10000, 80000, 60000] } df = pd.DataFrame(data) print(df)
Find Total Sales
total_sales = df["Total"].sum() print("Total Sales:", total_sales)
Find Average Sales
average_sales = df["Total"].mean() print("Average Sales:", average_sales)
Find Maximum Sales
maximum_sales = df["Total"].max() print("Maximum Sales:", maximum_sales)
13. Data Analytics vs Data Science
| Data Analytics | Data Science |
|---|---|
| Focuses mainly on analyzing data | Broader field involving data, statistics, and computing |
| Often explains existing data | Can build predictive and machine learning models |
| Uses Excel, SQL, Power BI, Python | Uses Python, R, SQL, ML frameworks, etc. |
| Focuses on insights and reporting | Can include prediction and automated decision systems |
| Common role: Data Analyst | Common roles: Data Scientist, ML Engineer |
14. Data Analytics vs Business Intelligence
| Data Analytics | Business Intelligence |
|---|---|
| Analyzes data to find insights | Focuses on reporting and monitoring business performance |
| Can include statistical analysis | Often emphasizes dashboards and reports |
| Uses historical and current data | Commonly uses historical and current business data |
| Can support predictive analysis | Commonly focuses on business reporting and KPIs |
| Tools include Python, SQL, Excel | Tools include Power BI, Tableau, Excel |
15. Real-Life Applications
Data Analytics is used in many areas.
Banking
- Fraud detection
- Customer analysis
- Risk analysis
- Transaction analysis
Healthcare
- Patient data analysis
- Hospital performance
- Disease research
- Resource planning
E-Commerce
- Customer behavior
- Product recommendations
- Sales analysis
- Inventory management
Education
- Student performance
- Attendance analysis
- Course performance
- Dropout analysis
Marketing
- Customer segmentation
- Campaign analysis
- Advertisement performance
- Market research
Transportation
- Traffic analysis
- Route optimization
- Fuel analysis
- Demand forecasting
Cybersecurity
- Threat detection
- Log analysis
- Anomaly detection
- Security monitoring
16. Advantages of Data Analytics
- Helps make data-driven decisions.
- Improves business performance.
- Identifies trends and patterns.
- Helps reduce operational costs.
- Improves customer understanding.
- Helps detect errors and fraud.
- Supports forecasting.
- Improves planning.
- Helps measure performance.
- Provides useful business insights.
17. Limitations of Data Analytics
- Poor-quality data can produce poor results.
- Data collection can be expensive.
- Analysis may require technical skills.
- Large datasets can be difficult to process.
- Privacy and security issues may occur.
- Incorrect analysis can lead to incorrect conclusions.
- Results may depend on the quality and representativeness of the data.
18. Data Analytics Career Roles
People with Data Analytics skills can work in roles such as:
- Data Analyst
- Business Analyst
- Business Intelligence Analyst
- Reporting Analyst
- Marketing Analyst
- Financial Analyst
- Operations Analyst
- Data Visualization Analyst
19. Simple Data Analytics Workflow
RAW DATA ↓ Data Collection ↓ Data Cleaning ↓ Data Preparation ↓ Exploratory Analysis ↓ Data Analysis ↓ Data Visualization ↓ Find Insights ↓ Decision Making
20. Key Points to Remember
- Data Analytics converts raw data into useful information.
- It helps organizations make data-driven decisions.
- Data cleaning is an important part of the analytics process.
- EDA helps understand the characteristics of data.
- Visualization makes data easier to understand.
- Excel, SQL, Python, Power BI, and Tableau are common analytics tools.
- The four major types are Descriptive, Diagnostic, Predictive, and Prescriptive Analytics.
- Data Analytics is widely used in business, healthcare, education, banking, marketing, transportation, and cybersecurity.
Conclusion
Data Analytics is an important field that helps convert raw data into meaningful insights. It combines data collection, cleaning, statistics, analysis, visualization, and interpretation to support better decision-making. Tools such as Excel, SQL, Python, Power BI, and Tableau make it easier to analyze large amounts of data and communicate useful results.