The document discusses business analytics and data visualization. It defines business analytics as the iterative and methodical exploration of an organization's data using statistical analysis to support data-driven decision making. It describes the main areas of business analytics techniques as business intelligence and statistical analysis. It also outlines the four main types of business analytics: descriptive, predictive, prescriptive, and diagnostic. The document further discusses data visualization, consumption of analytics, tools for data visualization, examples of data visualizations, and characteristics of effective graphical displays.
2. Business analytics (BA) is the
practice of
Iterative
methodical exploration of an
organization's data,
with an emphasis on statistical analysis.
Business analytics is used by companies
committed to data-driven decision-
making.
BUSINESS ANALYTICS
3. BA techniques break down into two main areas
Business intelligence
involves examining historical data to sense
how a business team performs over a
particular time
Statistical Analysis
doing predictive analytics by applying
statistical algorithms to historical data to
make prediction about future performance
about a product, service. Eg: Cluster analytics
BUSINESS ANALYTICS
Contd.,
4. TYPES OF BUSINESS ANALYTICS
4 types
Descriptive Analytics
tracks KPI (Key Performance Indicators) to
understand present state of business
Predictive Analytics
analyze trend data to asses the likelihood of
future outcomes
Prespective Analytics
Uses past performance and generate
recommendations to handle current
situations
Contd.,
5. Diagnostic Analytics
is a form of advance analytics that
examines data or content to answer the
question “Why did it happen”
Characterized by techniques such as drill
down data discovery, data mining and
correlations
TYPES OF BUSINESS ANALYTICS
Contd.,
6. Descriptive Analytics (BI) Predictive Analytics Prespective Analyticas
What and when did it
happen
What is likely to
happen next
What is the best answer
How much is the impact
and how often it happens
What if these trends
continue
What is the best outcome
given uncertainty
What is the problem What if What are significantly
differing and better
choices
Statistics
Datamining
Predictive Modelling
Machine learning
Forecasting
Simulation
Constraint-based
optimization.
Multi objective
optimization
Global Optimization
Information Management
TYPES OF BUSINESS ANALYTICS
8. Consumption Analytics is still an emerging
area, where companies are capturing lot of
clicks and data
That figures out the most valuable insights
The nature of consumption is different
among different technologies
Communication cycle provides a frame work
for making analytics consumable
CONSUMPTION ANALYTICS
Contd.,
10. Communication:
core intention take analysis beyond your core team
(i.e., wide group of decision makers)
Implement:
Getting right ingredients in place to create the basic
human and technology infrastructures
Measure:
This is the true test of anlaytics
a succession decision is a healthy combination of
business experience and data analytics
Align Incentives:
Develop Cognitive Repairs:
COMMUNICATION CYCLE
Contd.,
11. Align Incentives:
creates of more structured decision-making
processes
Puts a constraints on free-flowing, experience
driven decision making
Implementation will bring new incentives for a
single puzzle
Develop Cognitive Repairs:
Creation of counterintuitive business insights
based on data and proving it right
COMMUNICATION CYCLE
12. “ How to convert thought into action and
bridge the gap between analytics creation and
consumption”?
Do you have experience in creating a lot of
analytics but failing at consumption?
Does it make sense to ramp up/down
analytics creation to maintain balance with
consumption?
Human bias exists? Do you need to develop
structures that push people toward healthy
conflict and resolution?
CREATION TO CONSUMPTION
14. Def: “ It is form of visual communication of
information/data that has been abstracted in
some schematic form ”
The primary goal of data visualization is to
communicate information clearly and effectively
using statistical graphs, plots and information
graphs.
Old methods of data visualization are charts &
graphs
These things were done using two things
Describing: explain a thing for basic meaning
Reporting: summarize finding from point-in-time
DATA VISUALIZATION
Contd.,
15. New Methods of data visualization are
dynamic visualizations designed by data
artisans
Data aritisans/data artists are individuals
with intersection of skills in science, design,
and art
Observing: Viewing data to identify significance or
patterns which unfold over a period of time.
Discovering: Interacting with data to explore,
interact, and understand relationship between data
DATA VISUALIZATIONS
Contd.,
16. show the data
induce the viewer to think about the substance rather than
about methodology, graphic design, the technology of graphic
production or something else
avoid distorting what the data has to say
present many numbers in a small space
make large data sets coherent
encourage the eye to compare different pieces of data
reveal the data at several levels of detail, (bottom up
approach)
serve a reasonably clear purpose: description, exploration,
tabulation or decoration
be closely integrated with the statistical and verbal
descriptions of a data set.
CHARACTERISTICS OF EFFECTIVE
GRAPHICAL DISPLAYS
Contd.,
17. Data artisans are using many different dimensions to
represent and evaluate data:
Spatial, geospatial: position, direction, velocity
Temporal, periodicity: state, cycle, phase
Scale, granularity: weight, size, count
Relativity, proximity
Value, priority
Resources: energy, temperature, matter
Constraints
DATA VISUALIZATIONS
Contd.,
19. TYPES OF DATA VISUALIZATIONS
BASIC SCATTER PLOT
Visual Dimensions:
• X position
• Y position
• (symbol/glyph)
• (colour)
• (size)
Usage: define relationship
3D-SCATTER PLOT
Usage:3D analysis
Visual Dimensions:
• Position X
• Position Y
• Position Z
• colour
Contd.,
20. NETWORK ANALYSIS
Visual Dimensions:
• Nodes size
• Nodes colour
• Ties thickness
• Ties colour
• spatilization
Usage: Finding clusters in
network( grouping)
TREE MAP
Visual Dimensions:
• Size
• colour
Usage: disk space by location /
file type
TYPES OF DATA VISUALIZATIONS
Contd.,
22. Tableau, www.tableausoftware.com
Qlikview, www.qlikview.com
Microstrategy, www.microstrategy.com
D3JS, Data Driven Documents java script library,
http://d3js.org.
SAS, www.sas.com
Gephi Org, open-source data visualization platform.,
https://gephi.org
Arbor JS, a java-based graph library, http://arborjs.org
Cubism, a plug-in for D3 for visualizaing time series,
http://square,github.com/cubism
GeoCommons, a community building an open mapping
platform, http://geocommons.com
OPEN SOURCE TOOLS FOR
DATA VISUALIZATION
28. 90% or 9 think about the people analysts,
analysis and intelligence
10% or 1 work on tools and professional services
for data with different patterns
Where should they go?
What data will be more useful to consumers?
What metrics should we think about and what kind of
psychological analysis should we think about next
9/10 RULE OR 90/10 RULE
30. Def: “It is a mix of behavioral economics,
applied psychology, cognitive science, game
theory, statistics, risk analysis”
Or
‘Decision Sciences’ is a collaborative
approach involving mathematical formulae,
business tactics, technological applications
and behavioral sciences to help senior
management make data driven decisions
DECISION SCIENCE
Contd.,
31. Learning over knowing
Based on past domain must have ability to apply
principles and structured approaches for problem
solving
Agility
Update with continuous transformation
Scale and Convergence
Synergistic (co-operation of two or more
organizations)ecosystem of talent, capabilities,
processes, customers
Partners, domains, verticals
PROFESSIONAL TRAITS –
TO MAKE DECISION SCIENCE SUSTAINABLE
Contd.,
32. Multidisciplinary talent
Apply mathematics, business, technology, behaviour
together in business
Innovation
Increase breadth and depth of problem solving
Researching and deploying emerging trends,
technologies and applications
Cost Effectiveness
Ensure sustainability of problem solving across
organizations
PROFESSIONAL TRAITS –
TO MAKE DECISION SCIENCE SUSTAINABLE
Contd.,
33. Focus on nurturing of new employees
instead of labelelling
Be sure to give employees room to grow
Emphasize striving for a personal best
HOW CAN WE MAKE DECISION
SUSTAINABLE
34. When an organization expects the fruits
of analytics , the organizational structure
takes into account
the DNA of the organization
Culture
Overall goals
RIGHT ORGANIZATION STRUCTURE FOR
INSTITUTIONALIZING ANALYTICS
39. 7 Global principles
1. Notice (Transparency)-
- Informs individuals about the purpose for which
information is collected
2. Choice
- Offer an opportunity to users to choose how the
personal information can be disclosed
3. Consent
- disclose personal data information to third
parties with principles of notice and choice
4. Security
- Responsible to protect personal information from
- Loss, misuse, unauthorized access, disclosure,
alteration, destruction
GLOBAL PRIVACY PRINCIPLES
40. 5. Data Integrity
• Assure reliability of personal information
• Ensure information accuracy, complete, updated
• Must use for intended use only
6. Access
• Provide individuals to access their personal information
only
7. Accountability
• An organization must be accountable for the above said
principles
• And must include mechanisms for assuring compliance
(assuring the action)
GLOBAL PRIVACY PRINCIPLES