1

MBABA314 – Data Visualization

MODULE - 03
CLASSIFICATION OF VISUALIZATION SYSTEMS

CLASSIFICATION OF VISUALIZATION SYSTEMS

[Link]

Visualization systems can be classified based on their purpose, data complexity, and
interactivity level. These systems help transform raw data into meaningful insights through
graphical representation.
Type of Visualization
Description Examples / Tools
System
Printed charts, PDF
Static Visualization Display fixed visual representations;
reports, Excel static
Systems no user interaction.
graphs
Interactive Allow users to explore data using Power BI, Tableau,
Visualization Systems filters, drill-downs, or sliders. Google Data Studio
Dynamic / Real-Time Continuously update visuals as new Live dashboards for
Systems data streams in. sales or website traffic
Simulation tools,
3D and Immersive Present complex multi-dimensional
engineering and GIS
Visualization Systems data using 3D or VR environments.
software
Web-Based Accessible via browsers; ideal for Plotly Dash, Google
Visualization Systems shared business reporting. Looker Studio

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 2
MBABA314 – Data Visualization

COMMON VISUALIZATION TECHNIQUES

Data visualization is one of the most powerful tools in a business analyst's toolkit. As an MBA
student, you'll often find yourself drowning in spreadsheets filled with numbers. The ability to
transform these numbers into clear, compelling visuals can make the difference between a
confusing presentation and one that drives decision-making. This guide walks you through the
most essential visualization techniques you'll use throughout your career, from basic
comparisons to complex relationship analysis.

Think of visualizations as the language of data. Just as you wouldn't use the same tone in every
business communication, you shouldn't use the same chart for every dataset. Each visualization
technique serves a specific purpose, and choosing the right one depends on the story you're
trying to tell. Whether you're comparing sales across regions, tracking trends over time, or
uncovering hidden patterns, there's a visualization designed for that exact purpose.

Different visualization techniques serve different analytical purposes. Below are some of the
most commonly used visual tools in business analytics:

1. Bar Chart: Comparing Categories

Bar charts are the workhorses of business analytics. They display categorical data using
rectangular bars, where the length of each bar represents the value, it contains. When you need
to answer questions like "Which product line is performing best?" or "How do our sales
compare across different regions?", a bar chart is typically your first choice.
The beauty of bar charts lies in their simplicity and clarity. Your audience can instantly grasp
which categories are performing well and which need attention. Unlike pie charts, bar charts
make it easy to compare precise values because our eyes are naturally good at comparing
lengths along a common baseline. They work particularly well when you have anywhere from
two to fifteen categories to compare.

Example: Regional Sales Performance Analysis

Imagine you're a regional manager presenting quarterly sales results to senior leadership. You
have five regions to compare, and you need to show not just which region is winning, but by
how much. A bar chart makes these comparisons crystal clear, allowing executives to quickly
identify that the West region is outperforming others significantly, while the Midwest needs
strategic attention.

2. Line Chart: Tracking Trends Over Time

Line charts connect data points with lines to show how values change over time. They're
essential for spotting trends, identifying patterns, and understanding the trajectory of your
business metrics. Whether you're tracking monthly revenue, website traffic, or stock prices,
line charts help you see not just where you are, but where you're heading.
What makes line charts particularly valuable is their ability to show momentum and direction.
A rising line tells a story of growth, while a falling line signals the need for intervention. You
can also compare multiple lines on the same chart to see how different products, regions, or
strategies are performing relative to each other. This makes them indispensable for
performance dashboards and executive reports.

Example: Monthly Revenue Tracking

As a financial analyst, you need to present the company's revenue performance over the past
year to the board of directors. A line chart reveals not just the numbers, but the story behind
them: strong growth in Q1 and Q2, a summer slump, and a successful recovery in Q4. This

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 3
MBABA314 – Data Visualization

visualization helps leadership understand seasonal patterns and evaluate the effectiveness of
strategic initiatives.

3. Scatter Plot: Uncovering Relationships

Scatter plots display individual data points on a two-dimensional graph, with one variable on
the X-axis and another on the Y-axis. They're your go-to tool when you want to understand if
and how two variables are related. Do higher advertising budgets lead to increased sales? Does
employee experience correlate with productivity? Scatter plots help answer these questions
visually.
The power of scatter plots lies in pattern recognition. When points cluster along an upward
diagonal, you're seeing a positive correlation. A downward diagonal suggests a negative
relationship, while scattered points with no clear pattern indicate little or no correlation. This
makes scatter plots invaluable for exploratory analysis, helping you identify relationships that
might warrant deeper investigation or inform strategic decisions.

Example: Marketing Investment vs. Sales Performance

Your marketing team wants to justify their budget request for next quarter. By plotting monthly
advertising spend against resulting sales revenue, you can demonstrate the relationship between
investment and returns. The scatter plot reveals a clear positive correlation: higher marketing
spend consistently leads to increased sales, providing data-driven justification for the budget
increase.

4. Pie Chart / Donut Chart: Showing Proportions

Pie charts divide a circle into slices, where each slice represents a proportion of the whole.
They answer the question "What percentage of the total does each category represent?" Donut
charts are simply pie charts with a hollow center, offering space for additional labels or
summary statistics while maintaining the same proportional representation.
While pie charts are among the most recognizable visualizations, they work best with a limited
number of categories—ideally between two and six. They're perfect when your message
focuses on composition rather than comparison. For instance, if you want to emphasize that
one product line accounts for half your revenue, a pie chart makes this immediately apparent.
However, when you have many similar-sized slices or need precise comparisons, bar charts are
usually more effective.

Example: Market Share Distribution

You're analyzing the competitive landscape of the smartphone market for a strategy
presentation. A pie chart effectively communicates that the market is dominated by four major
players who collectively control 95% of sales. This visualization helps leadership understand
both the company's position and the competitive dynamics at a glance.

5. Heatmap: Visualizing Intensity and Patterns

Heatmaps use color gradients to represent data intensity or frequency across two dimensions.
Darker or more vibrant colors typically indicate higher values, while lighter shades represent
lower values. This technique excels at revealing patterns that might be invisible in traditional
tables or charts, making it invaluable for analyzing large datasets where you need to spot
hotspots or anomalies quickly.
Heatmaps are particularly useful in business contexts where you're dealing with matrices of
data. Website analytics teams use them to see which page elements get the most clicks.
Retailers use them to understand peak shopping hours across different store locations. The
color coding provides instant visual feedback, allowing stakeholders to identify problem areas
or opportunities without wading through rows of numbers.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 4
MBABA314 – Data Visualization

Example: Customer Activity Heatmap

As an e-commerce manager, you need to optimize staffing and promotional timing. A heatmap
showing website traffic by day and hour reveals clear patterns: heavy traffic on weekday
evenings and weekend afternoons, with dead zones on weekday mornings. This insight directly
informs staffing schedules, email campaign timing, and flash sale planning.

6. Treemaps: Hierarchical Data Visualization

Treemaps display hierarchical data as nested rectangles, where the size of each rectangle
represents its value or importance. Think of it as a space-efficient way to show both hierarchy
and proportion simultaneously. Larger rectangles represent larger values, and rectangles are
grouped together to show their category relationships. This makes treemaps perfect for
visualizing complex data structures like organizational budgets, product portfolios, or file
system storage.
The key advantage of treemaps is their ability to show multiple levels of information at once.
You can see the big picture—which major categories dominate—while also drilling into
subcategories to understand the details. This makes them particularly valuable for portfolio
analysis, where you need to understand both overall composition and the contribution of
individual items within each category.

Example: Revenue by Product Category

Your company sells multiple product lines across different categories. A treemap allows the
executive team to instantly see that Electronics dominates revenue, understand how different
product subcategories contribute within Electronics, and identify which smaller categories
might be worth expanding or discontinuing. The visual hierarchy makes complex portfolio
decisions more intuitive.

7. Histogram: Understanding Data Distribution

Histograms show how data is distributed across different ranges or "bins." Unlike bar charts
that compare categories, histograms reveal the frequency of numerical values. They answer
questions like "How many customers fall into each age group?" or "What's the typical purchase
amount?" By showing the shape of your data distribution, histograms help you understand
central tendencies, spread, and outliers.
Understanding distribution is crucial for business decision-making. A histogram of customer
purchase amounts might reveal that most customers spend between $50-$100, with a long tail
of high-value customers. This insight could inform pricing strategy, inventory management,
and marketing segmentation. Histograms also help you spot unusual patterns—like bimodal
distributions suggesting two distinct customer segments—that warrant further investigation.

Example: Customer Purchase Amount Distribution

As a retail analyst, you're studying customer behavior to optimize pricing and promotions. A
histogram of purchase amounts reveals that the majority of transactions cluster in the $40-$80
range, with a small but significant group making purchases above $150. This distribution
suggests a two-tier customer base: regular shoppers and premium buyers who might respond
to different marketing strategies.

8. Box Plot: Analyzing Spread and Outliers

Box plots (also called box-and-whisker plots) provide a statistical summary of data distribution,
showing the median, quartiles, and outliers in a compact format. The "box" represents the
middle 50% of data, the line inside shows the median, and the "whiskers" extend to show the
data range, with any points beyond being potential outliers. This makes box plots invaluable
when you need to compare distributions across groups or identify unusual values.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 5
MBABA314 – Data Visualization

For business analysts, box plots are particularly useful when comparing performance across
different segments. They show not just average performance, but also consistency and
variability. A sales team with a tight box plot has consistent performance, while one with a
wide box and many outliers might have a few star performers and several struggling members.
This insight drives different management approaches.

Example: Employee Salary Distribution by Department

The HR team needs to assess salary equity and competitiveness across departments. Box plots
reveal that while the Engineering department has the highest median salary, the Sales
department shows much greater variability—suggesting a commission-heavy compensation
structure. The visualization also highlights potential outliers that merit investigation: Are these
exceptional performers, or are there equity issues to address?

9. Bubble Chart: Three Variables in One View

Bubble charts extend scatter plots by adding a third dimension: bubble size. While the X and
Y axes show two variables, the size of each bubble represents a third variable, allowing you to
visualize three related metrics simultaneously. This makes bubble charts powerful for complex
analysis where multiple factors interact, such as evaluating product portfolios or comparing
market opportunities.
The challenge with bubble charts is avoiding visual clutter. They work best with a moderate
number of data points—typically fewer than twenty—so each bubble remains distinct and
interpretable. When used effectively, bubble charts can reveal insights that would require
multiple separate visualizations, helping stakeholders understand multifaceted business
situations at a glance.

Example: Product Performance Analysis

As a product manager, you need to evaluate your entire product portfolio to decide where to
invest development resources. A bubble chart plotting sales revenue (X-axis) against profit
margin (Y-axis), with bubble size representing market share, creates a powerful strategic tool.
You can instantly identify your "star" products (high sales, high margin, large market share),
"cash cows" (high sales, lower margin), and opportunities (high margin but low sales that might
benefit from marketing investment).

10. Geospatial Map: Location-Based Insights

Geospatial maps plot data points based on geographic location, transforming numerical data
into visual geography. They're essential when location matters to your analysis—whether
you're optimizing delivery routes, analyzing regional sales patterns, identifying expansion
opportunities, or understanding customer demographics. By overlaying business data onto
maps, you make location-based patterns immediately apparent.
Modern geospatial visualizations go beyond simple pin drops. They can use color intensity to
show regional performance, use bubble size to represent volume, or draw heat maps to identify
geographic clusters. This makes them invaluable for businesses with physical presence or
geographic variation in their customer base. Location-based insights often reveal opportunities
or problems that aren't visible in traditional charts.

Example: Regional Sales Distribution and Logistics Planning

Your company operates across multiple states and needs to optimize warehouse locations and
distribution routes. A geospatial map showing sales volume by region reveals that the Northeast
and West Coast generate the highest revenue but are served by distant warehouses, resulting in
higher shipping costs and longer delivery times. This visualization provides clear justification
for opening new distribution centers in these high-demand regions.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 6
MBABA314 – Data Visualization

Common Visualization Dashboards

[Link]

Technique Purpose / Use Case Example Application

Bar Chart Compare categorical data across Sales by region, product
groups. performance
Line Chart Show trends or changes over Monthly revenue or stock price
time. trend
Scatter Plot Visualize relationships or Advertising spends vs. sales
correlations between two revenue
variables.
Pie Chart / Show proportion or percentage Market share by brand
Donut Chart contribution.
Heatmap Represent intensity or frequency Customer density, website clicks,
using color gradients. or transaction volume
Tree map Display hierarchical data as Product categories and
nested rectangles. subcategories contribution to
revenue
Histogram Show data distribution or Distribution of customer ages or
frequency. purchase amounts
Box Plot Display spread and outliers in Employee salary distribution
numerical data.
Bubble Chart Represent three variables using X, Sales (X), profit (Y), and market
Y, and bubble size. share (bubble size)
Geospatial Map Plot data points based on location. Regional sales, logistics routes, or
customer distribution

Merits & Demerits of Visualization Techniques

Technique Merits Demerits
• Can become cluttered with too many
• Simple and easy to interpret. categories.
• Clearly compares categorical data. • Not ideal for showing trends over
Bar Chart
• Works well for both small and large time.
datasets. • Overlapping bars can reduce
readability.
• Excellent for showing trends and
changes over time. • Hard to interpret with too many lines.
• Easy to compare multiple time • Not suitable for categorical data.
Line Chart
series. • Sudden spikes can be misleading
• Visually intuitive for continuous without context.
data.
• Can be confusing with large datasets
• Reveals relationships and
(overplotting).
correlations between variables.
• Not useful for categorical
Scatter Plot • Identifies clusters and outliers
comparisons.
easily.
• Requires statistical interpretation for
• Effective for regression analysis.
accurate insights.
Pie Chart / • Simple way to show proportion or • Difficult to compare many slices
Donut Chart percentage share. accurately.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 7
MBABA314 – Data Visualization

• Visually appealing for small • Not suitable for showing changes over
datasets. time.
• Easy to understand for non-technical • Misleading if proportions are similar
audiences. or numerous.
• Effectively shows intensity or • Can be hard to interpret without a
frequency patterns. proper color legend.
• Great for large datasets and visual • Not suitable for precise value
Heatmap
pattern recognition. comparisons.
• Highlights areas of high or low • Poor color choices can distort
concentration instantly. perception.
• Represents hierarchical data
compactly. • Difficult to compare rectangles of
• Efficiently shows part-to-whole similar size.
Tree Map
relationships. • Labels can overlap or be hard to read.
• Useful for visualizing proportions • Not effective for trend analysis.
within categories.
• Shows frequency distribution of
• Choice of bin size can affect
continuous data.
interpretation.
Histogram • Useful for identifying data spread,
• Not useful for categorical data.
skewness, and patterns.
• Cannot show exact data values.
• Helps in detecting outliers.
• Displays data spread, median, and • Hard for non-technical users to
outliers clearly. interpret.
• Good for comparing multiple groups • Does not show data distribution
Box Plot
statistically. details.
• Summarizes large datasets • Less visually engaging than other
effectively. charts.
• Shows three variables • Can become cluttered or confusing
simultaneously (X, Y, and size). with many bubbles.
Bubble • Engaging and useful for • Hard to interpret bubble size
Chart multidimensional comparisons. accurately.
• Helps identify clusters and • Not suitable for precise value
correlations. representation.
• Visually represents data with a
• Requires accurate geographic data.
location context.
• Can be misleading if area size biases
Geospatial • Useful for regional or geographic
perception.
Map analysis.
• Complex to interpret without proper
• Supports interactive, real-world
scale or legend.
insights.

Choosing the Right Visualization: A Quick Decision Guide

With so many visualization options available, selecting the right one can feel overwhelming.
Here's a simple decision framework:
Ask yourself: What question am I trying to answer?
• "Which category is largest/smallest?" → Bar Chart
• "How has this changed over time?" → Line Chart
• "Are these two variables related?" → Scatter Plot
• "What proportion does each part represent?" → Pie Chart
• "Where are the patterns or hotspots?" → Heatmap
• "How is this hierarchy composed?" → Treemap
• "How is this data distributed?" → Histogram

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 8
MBABA314 – Data Visualization

• "How do groups compare statistically?" → Box Plot

• "How do three variables interact?" → Bubble Chart
• "Where geographically is this happening?" → Geospatial Map

Common Mistakes to Avoid

Even experienced analysts make visualization errors. Here are the most common pitfalls to
watch out for:
✓ Starting bar charts at non-zero values. This distorts comparisons and can be
misleading. Always start your Y-axis at zero for bar charts to accurately represent
relative differences.
✓ Using too many colors. Excessive color variation distracts rather than clarifies. Stick
to a simple, consistent color palette, using color to highlight important information
rather than decorate every element.
✓ Choosing 3D charts unnecessarily. While 3D effects might look sophisticated, they
make accurate reading difficult and often distort the data. Stick to 2D visualizations
unless you genuinely need to represent three-dimensional data.
✓ Overcrowding your visualization. Including too many data points, labels, or
categories creates visual clutter that obscures your message. If your chart looks busy,
consider splitting it into multiple focused visualizations or filtering to show only the
most relevant data.
✓ Ignoring your audience. Technical audiences might appreciate complex statistical
visualizations, while executive audiences need clear, simple charts that support
decision-making. Always consider who will view your visualization and what they need
to understand.

Conclusion: From Data to Decision

Mastering these ten visualization techniques transforms you from someone who reports
numbers to someone who tells data stories. Each technique serves a specific purpose, and
knowing when to use each one is as important as knowing how to create them. As you progress
in your MBA journey and beyond, you'll develop an intuition for which visualization best
serves your analytical goals.
The key to effective data visualization isn't just technical skill—it's understanding your
audience, clarifying your message, and choosing the right tool for the job. Start with simple,
clear visualizations. As you gain experience, you'll know when added complexity serves your
purpose and when it merely adds confusion. Remember, the goal of any visualization is to
make complex data understandable and actionable. If your chart doesn't do that, it's not the
right chart.
Practice with real datasets, experiment with different approaches, and always ask yourself:
"Does this visualization make my message clearer or more confusing?" With these ten
techniques in your toolkit, you're well-equipped to turn data into insights and insights into
action.

VISUALIZATION OF ONE, TWO & MULTI-DIMENSIONAL BUSINESS

DATA

One-Dimensional Data Visualization

One-dimensional data is the simplest form of business data, representing a single variable or
metric. This data answers questions about quantity or frequency without requiring a
relationship to another measure. Since the focus is on magnitude, visualizations primarily use
the length or height of an element to represent the value. Common visualization examples

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 9
MBABA314 – Data Visualization

include bar charts, column charts, and histograms. In a business context, this is typically used
for basic performance tracking, such as displaying the total revenue achieved each month, the
headcount in each department, or the frequency of customer service calls. These visualizations
are straightforward, prioritizing clarity and direct interpretation.

Two-Dimensional Data Visualization

Two-dimensional data involves two distinct variables that are analyzed together to explore
relationships, correlations, or direct comparisons. This form of data allows businesses to
answer relational questions like "How does X affect Y?" or "How does performance compare
between two groups?" Visualization examples include line charts (for trends over time), scatter
plots (for correlation), and grouped bar charts (for comparisons). A classic business application
is a scatter plot analyzing the relationship between sales volume (Y-axis) and advertising spend
(X-axis) to determine the return on investment (ROI) or a line chart showing a comparison of
profit margin across two different sales regions over a quarter.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 10
MBABA314 – Data Visualization

Multi-Dimensional Data Visualization

Multi-dimensional data includes three or more variables (dimensions), making it necessary to
use multiple visual cues simultaneously to represent the complexity. Visualizations for this
data are often highly interactive and utilize visual properties like size, color, depth, and
clustering to encode the additional variables. Key examples are bubble charts (using X, Y, and
size), heatmaps (using two axes and color intensity), treemaps (using area and color), and
interactive pivot dashboards. The primary business application is complex performance
analysis, such as using a bubble chart to visualize: Sales revenue (X-axis), Profit (Y-axis), and
Customer Satisfaction (bubble size), further broken down by Region (color). This approach
allows analysts to gain comprehensive insights, such as identifying a region with high sales
and profit but low customer satisfaction, signaling a potential long-term risk.

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 11
MBABA314 – Data Visualization

Visualization
Dimension Description Business Application
Examples
One- Displaying total sales
Represents a single Bar chart, column
Dimensional or employee count per
variable or metric. chart, histogram
Data department.
Two- Involves two variables Line chart, scatter Analyzing sales vs.
Dimensional to explore relationships plot, grouped bar advertising spend or
Data or comparisons. chart profit by region.
Visualizing sales (X),
Includes three or more Bubble chart,
Multi- profit (Y), and
variables, often heatmap, Treemap,
Dimensional customer satisfaction
requiring complex or radar chart, pivot
Data (Z) across multiple
interactive visuals. dashboards
regions.

BUSINESS-FRIENDLY DATA STRUCTURES FOR DECISION-MAKING

1. Tabular Data
Tabular data is the most common and straightforward structure used in business analytics. It is
organized in rows and columns, similar to a spreadsheet or database table. Each row represents
a single record or observation, while each column represents a specific attribute or variable.
This format is ideal for storing structured, categorical, or numerical data that can be easily
analyzed using tools such as Microsoft Excel, Google Sheets, or Business Intelligence
platforms like Power BI or Tableau.

Business Application: Tabular data supports quick insights into performance metrics such as
sales summaries, customer demographics, or inventory levels. It’s easy to aggregate, filter, and
visualize, making it a foundational structure for reporting and analysis.

Sample Dataset — Sales Performance Table

Region Product Q1_Sales Q2_Sales Q3_Sales Q4_Sales Total_Sales
North Laptop 50000 65000 72000 80000 267000
South Tablet 40000 42000 50000 55000 187000
East Phone 30000 35000 37000 39000 141000

2. Hierarchical Data
Hierarchical data is structured in multiple levels, where each level represents a parent-child
relationship. This means that data elements are linked in a tree-like structure — for example, a
company → departments → teams → employees. Such structures are essential for representing
data that naturally follows a hierarchy, such as organizational charts, product categories, or file
systems.

Business Application: Hierarchical data helps in analyzing relationships between broader

categories and their subcomponents, such as sales across product families or performance
across business units.

Sample Dataset — Product Category Hierarchy

Category Subcategory Product Sales
Electronics Computers Laptop 120000
Electronics Mobile Devices Smartphone 90000
Home Appliances Kitchen Microwave 40000
Home Appliances Cleaning Vacuum Cleaner 35000

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 12
MBABA314 – Data Visualization

3. Time-Series Data
Time-series data represents information recorded over consistent time intervals—such as daily,
weekly, monthly, or yearly observations. This structure is essential for analyzing trends,
forecasting, and monitoring changes over time. Each data point typically has two components:
a timestamp and a value.

Business Application: Organizations use time-series data to analyze sales growth, monitor
stock prices, measure website traffic, or track production output over time. Time-series
visualization (like line charts) helps in identifying seasonal patterns or predicting future
outcomes.

Sample Dataset — Monthly Revenue Trend

Month Revenue (₹)
January 1,20,000
February 1,35,000
March 1,40,000
April 1,55,000
May 1,80,000

4. Geospatial Data
Geospatial data includes information tied to geographic locations—such as coordinates, postal
codes, or regions. It helps visualize and analyze patterns based on location. Data can be
represented as points (e.g., store locations), lines (e.g., delivery routes), or polygons (e.g., sales
territories). Tools like GIS (Geographic Information Systems), Google Maps, or Power BI
maps are used to display and interpret geospatial datasets.

Business Application: Businesses leverage geospatial data for market segmentation, logistics
optimization, territory management, and location-based marketing.

Sample Dataset — Store Location and Performance

Store_ID City Latitude Longitude Monthly_Sales (₹)
S001 Bengaluru 12.9716 77.5946 2,50,000
S002 Chennai 13.0827 80.2707 1,90,000
S003 Hyderabad 17.3850 78.4867 2,10,000
S004 Mumbai 19.0760 72.8777 2,80,000

5. Multidimensional (OLAP) Cubes

Multidimensional data structures, often implemented as OLAP (Online Analytical Processing)
cubes, allow data to be viewed and analyzed across multiple dimensions simultaneously.
Unlike flat tables, OLAP cubes enable slicing (viewing one dimension), dicing (filtering across
dimensions), and aggregating (summarizing) data for faster decision-making. Common
dimensions include time, geography, product, and sales channel.

Business Application: OLAP cubes are central to Business Intelligence systems, enabling
executives to perform “what-if” analysis, compare regional performances, or analyze
profitability across time periods and product categories.

Sample Dataset — Sales Cube (Dimensions: Region, Product, Quarter)

Region Product Quarter Sales (₹)
North Laptop Q1 50,000
North Laptop Q2 65,000

Prof. Srinivas S, Dept of MBA & RC, SJCIT

 13
MBABA314 – Data Visualization

North Tablet Q1 40,000

South Laptop Q3 70,000
South Phone Q4 55,000
(Dimensions: Region, Product, Quarter; Measure: Sales)

For effective visualization and analysis, data must be structured in ways that align with
business objectives and analytical models.

Data Structure Description Business Use

Organized in rows and columns,
Sales reports, customer
Tabular Data easy to analyze in Excel or BI
lists
tools.
Data arranged in levels or Product category → sub-
Hierarchical Data
categories. category → item
Sequential data recorded over time Revenue, website traffic,
Time-Series Data
intervals. production output
Data associated with geographic Store locations, delivery
Geospatial Data
coordinates. zones
Structured for slicing, dicing, and Decision support systems,
Multidimensional
aggregating data across multiple business intelligence
(OLAP) Cubes
dimensions. cubes

Use clean, validated, and well-labelled data structures to ensure accuracy in dashboards
and visualizations. A well-organized dataset supports faster insights, trend discovery, and
confident decision-making.

Prof. Srinivas S, Dept of MBA & RC, SJCIT