Disruptive Technologies

LECTURE 10

Data Analytics With Tools

Dr. Tamal Ghosh, Department of Computer Science and Engineering, A

damas University
Understanding the Four Pillars of Analytics: Descriptive,
Diagnostic, Predictive, and Prescriptive

1. Descriptive Analytics:
• What happened?
• Key metrics: Summarize past performance, trends, and
patterns using tools like statistical measures
(averages, percentages), data visualization
(charts, graphs), and reports.
• Applications: Understanding sales trends, website traffic
analysis, and customer segmentation.
Contd…
2. Diagnostic Analytics:
• Why did it happen?
• Deeper dive: Examines the underlying causes and relationships
behind patterns observed in descriptive analysis. Uses
techniques like data mining, correlation analysis, and anomaly
detection.
• Applications: Investigating root causes of customer
churn, identifying factors influencing sales decline, and
diagnosing equipment failures.
Contd…

3. Predictive Analytics:
• What is likely to happen?
• Forecasting: Leverages historical data and statistical models
to predict future outcomes, trends, and
probabilities. Techniques include regression analysis, time
series forecasting, and machine learning.
• Applications: Predicting sales demand, forecasting customer
behavior, anticipating equipment maintenance needs.
Contd…

4. Prescriptive Analytics:
• What should we do?
• Recommendations: Goes beyond prediction to suggest optimal actions and
strategies based on insights from all preceding analytics. Uses optimization
techniques, simulation, and decision science.
• Applications: Designing targeted marketing campaigns, optimizing resource
allocation, and setting personalized pricing strategies.
 Remember:
• These analytics types are not mutually exclusive; they build upon each other.
• Effective data analysis often involves applying all four types to gain a
comprehensive understanding and take informed actions.
• The specific tools and techniques used will vary depending on the specific
problem and industry.
Introduction To Microsoft Excel For Data
Analysis

Microsoft Excel, a widely used spreadsheet application, is

a versatile tool for data analysis that offers a user-friendly
interface and powerful features.
It is an accessible starting point for individuals and
businesses to unlock valuable insights from their data
without the need for advanced statistical or programming
knowledge.
 Key Features of Microsoft Excel for Data
Analysis

 Data Entry and Management:

Excel provides a structured environment for entering and managing data. Users can
input and organize data in rows and columns, making it easy to work with structured
datasets.
 Data Cleaning and Transformation:
Excel offers functions and tools for data cleaning, including removing duplicates,
handling missing values, and transforming data. This ensures that the data is accurate
and ready for analysis.
 Formulas and Functions:
Excel's wide range of built-in formulas and functions simplifies mathematical
calculations, statistical analysis, and data manipulation. Users can perform tasks like
summing, averaging, and finding standard deviations with ease.
 Data Visualization:
Excel allows users to create various types of charts and graphs to visualize data. This
makes it easier to identify trends, patterns, and anomalies in the data.
Contd…
 PivotTables and PivotCharts:
PivotTables and PivotCharts enable users to summarize and analyze large datasets
quickly. These features are particularly useful for aggregating data and generating
reports.
 What-If Analysis:
Excel's "Goal Seek" and "Solver" tools allow users to perform what-if analysis,
helping in decision-making by exploring different scenarios and their impacts.
 Data Analysis ToolPak:
Excel includes the Data Analysis ToolPak, which offers advanced statistical functions
such as regression analysis, analysis of variance, and exponential smoothing.
 Power Query and Power Pivot:
Advanced users can leverage Power Query to import and transform data from
various sources and Power Pivot for data modeling and analysis in more complex
scenarios.
Applications of Excel in Data Analysis
Financial Analysis: Excel is widely used for financial modeling,
budgeting, and forecasting. It helps organizations make informed
financial decisions.

Sales and Marketing Analysis: Businesses use Excel to analyze sales

data, track marketing campaigns, and identify customer trends.

Data Reporting: Excel is a popular tool for creating reports and

dashboards, presenting data in a visually appealing format for
stakeholders.

Scientific Research: Researchers use Excel for data collection,

statistical analysis, and graphing results.
Contd…
Inventory Management: Excel can be employed to track
inventory levels, reorder points, and inventory turnover.

Project Management: Project managers use Excel to create

Gantt charts, track project progress, and manage
resources.

Data Exploration: Excel is an accessible tool for exploratory

data analysis, enabling users to gain insights into data
before more advanced analysis.
Data Visualization With Advanced Tools
Data visualization is a crucial aspect of data analysis, as it
enables the transformation of complex datasets into clear,
visual representations.
While basic data visualization tools like Microsoft Excel and
Google Sheets serve well for simple charts and graphs,
advanced data visualization tools offer a broader spectrum
of capabilities, empowering analysts to create more
sophisticated and interactive visualizations.
Here, we explore the world of advanced data visualization
tools and their significance.
Key Features of Advanced Data Visualization
Tools
 Interactive Dashboards: Advanced tools allow you to build interactive dashboards
where users can explore data, filter, and drill down for deeper insights.
 Customization: These tools provide extensive options for customization, including
color schemes, fonts, and layout design to align with branding or specific data
requirements.
 Real-time Data: Some advanced tools can connect to live data sources, enabling real-
time updates and dynamic visualizations.
 Complex Data Integration: They support the integration of data from multiple
sources, including databases, APIs, and external platforms.
 Machine Learning Integration: Machine learning algorithms can be incorporated to
provide predictive analytics within the visualization.
 Geospatial Visualizations: Advanced tools often offer geospatial mapping capabilities,
enabling the visualization of data on maps and geographical analysis.
 Big Data Handling: Some tools are capable of handling large datasets, making them
suitable for big data analytics.
Popular Advanced Data Visualization
Tools
 Tableau: Known for its user-friendly interface and powerful capabilities, Tableau allows
users to create interactive dashboards, reports, and maps. It integrates well with
various data sources.
 QlikView and Qlik Sense: These tools provide associative data models and offer
interactive and self-service analytics for users to explore data relationships.
 Power BI: Microsoft's Power BI is known for its integration with other Microsoft
products. It enables the creation of dynamic reports and dashboards.
 D3.js: A JavaScript library, D3.js provides a high level of customization for data
visualizations, including interactive charts and graphs.
 Looker: Looker is a data exploration and business intelligence platform that allows for
custom reporting and exploration of data.
 Plotly: Plotly is an open-source graphing library for Python and R, enabling interactive
data visualization.
 Google Data Studio: Google's tool offers easy integration with various data sources,
including Google Analytics, and allows the creation of dynamic reports and
dashboards.
TABLEAU vs. Power bi
Applications of Advanced Data
Visualization
 Business Intelligence: Businesses use advanced visualization to gain
insights into sales, customer behavior, and market trends.
 Healthcare: Advanced visualization aids in medical imaging, patient
outcomes analysis, and healthcare resource management.
 Finance: Financial analysts utilize advanced tools to visualize market
data, portfolio performance, and risk analysis.
 Research and Development: Researchers rely on advanced visualization
for data exploration, results communication, and scientific discovery.
 IoT and Sensor Data: Visualizing data from IoT devices and sensors is
critical for monitoring and decision-making in various industries.
 Government and Public Policy: Public agencies use advanced
visualization for public policy analysis, census data, and urban planning.