Learning Objectives
By the end of this chapter, you will be able to:
- Define Data Analytics and distinguish it from related terms like Data Mining.
- Identify the four main types of Data Analytics.
- Describe the steps of the data analytics process.
- Name common data analytics tools.
- Understand the practical applications and challenges of Data Analytics in business.
What is Data Analytics?
Data Analytics is the systematic computational analysis of data or statistics to discover useful information, inform conclusions, and support decision-making. While Data Science is the broader field and Data Mining is the technique of discovering hidden patterns, Data Analytics is the practice of applying those findings to answer specific business questions.
Think of it this way:
- Data Science = The discipline
- Data Mining = The excavation technique
- Data Analytics = The act of examining and interpreting the results
The Four Types of Data Analytics
1. Descriptive Analytics
Answers the question: “What happened?”
- Summarizes past data into readable formats (reports, dashboards).
- Example: A monthly sales report showing revenue by product category.
2. Diagnostic Analytics
Answers the question: “Why did it happen?”
- Drills down into data to identify the root causes of outcomes.
- Example: Analyzing why sales dropped in a particular region by looking at marketing spend, competition, and website traffic.
3. Predictive Analytics
Answers the question: “What will happen?”
- Uses statistical models and machine learning to forecast future outcomes.
- Example: Predicting customer churn so a company can proactively retain at-risk customers.
4. Prescriptive Analytics
Answers the question: “What should we do?”
- Goes beyond prediction to recommend actions to achieve a desired outcome.
- Example: An e-commerce engine recommending specific discounts to specific customers to maximize the probability of a purchase.
flowchart LR
D[Descriptive: What happened] --> DI[Diagnostic: Why it happened]
DI --> P[Predictive: What will happen]
P --> PR[Prescriptive: What should we do]
Figure 1: Four Types of Data Analytics Pipeline
As a business moves from descriptive to prescriptive analytics, both the value of the insight and the difficulty of the analysis increase.
The Data Analytics Process
- Ask — define the business question (e.g., “Why are repeat orders falling?”).
- Collect — gather data from sales systems, websites, surveys, or social media.
- Clean — fix errors, remove duplicates, and handle missing values.
- Analyze — calculate summaries, compare groups, find trends and correlations, or build models.
- Visualize and share — present findings in charts and dashboards that managers can understand.
- Act — make a decision and measure its result.
Worked Example
An online grocery store in Kathmandu reviews its quarterly sales:
| Month | Orders | Revenue (Rs.) | Average order value (Rs.) |
|---|---|---|---|
| Shrawan | 2,000 | 3,000,000 | 1,500 |
| Bhadra | 1,800 | 2,520,000 | 1,400 |
| Ashwin | 2,600 | 4,420,000 | 1,700 |
- Descriptive: revenue fell about 16% in Bhadra, then rose about 75% in Ashwin.
- Diagnostic: drilling down shows Bhadra’s drop came from a delivery delay problem in one area, while Ashwin’s rise came from Dashain shopping.
- Predictive: based on previous years, the store forecasts a similar peak before Tihar.
- Prescriptive: it hires extra delivery riders and stocks festival items two weeks early.
Common Data Analytics Tools
| Tool | Typical use |
|---|---|
| Microsoft Excel | Sorting, formulas, PivotTables, and charts for small datasets |
| SQL | Retrieving and summarizing data from databases |
| Power BI / Tableau | Interactive dashboards and visual reports |
| Google Analytics | Website visitor and conversion analysis |
| Python / R | Advanced statistics, automation, and machine learning |
Business Applications
- Marketing: Analyzing campaign performance to optimize ad spend.
- Finance: Fraud detection and credit risk assessment.
- Supply Chain: Demand forecasting and inventory optimization.
- Healthcare: Predicting patient readmissions and optimizing hospital resource allocation.
- Human Resources: Understanding staff turnover and planning recruitment.
Nepal context
- Banks and financial institutions analyze transaction data to detect unusual activity and assess loan risk.
- Telecom operators analyze usage patterns to design data packs and offers.
- E-commerce and delivery companies analyze order data to plan inventory, delivery routes, and festival promotions.
- Digital marketers use analytics from Facebook and Google to measure which ads produce customers.
Challenges
- Poor data quality — incomplete or inaccurate data leads to wrong conclusions.
- Shortage of skills — analysts need statistics, tools, and business understanding.
- Data privacy — customer data must be protected and used responsibly.
- Misinterpretation — correlation is not causation; a pattern does not always explain why something happened.
- Data silos — data scattered across departments is hard to combine.
Summary
Data Analytics is the cornerstone of the modern data-driven organization. By progressing from descriptive to prescriptive analytics, businesses can move from simply understanding their past to actively shaping their future. A structured process—ask, collect, clean, analyze, visualize, and act—supported by tools from Excel to Power BI and Python, turns raw data into decisions. In Nepal and globally, demand for data analysts in marketing, finance, and operations continues to grow rapidly, though data quality, skills, and privacy remain challenges.
Key Takeaways
- Data analytics examines data to answer business questions and support decisions.
- The four types are descriptive, diagnostic, predictive, and prescriptive analytics.
- The process: ask, collect, clean, analyze, visualize, act.
- Common tools include Excel, SQL, Power BI, Tableau, Google Analytics, Python, and R.
- Challenges include data quality, skills, privacy, and misinterpretation.
Review Questions
- Define data analytics. How does it differ from data mining?
- Explain the four types of data analytics with business examples.
- Describe the steps of the data analytics process.
- How can a Nepali retail business use data analytics to improve sales?
