Data Discovery & Visualization - New
Data Discovery & Visualization - New
Data Discovery & Visualization - New
Discovery &
Visualizatio
n
TEAM 2
ADHARSH R - 2019201002
AT H I R A G O P I N A T H A N - 2019201013
G A YA T H R I V - 2019201023
MADESH V V – 2019201034
RA J A B H A RT H I - 2019201045
2. Cleanse and prepare data - Data needs to be cleaned and structured in ways that facilitate
reliable and robust analysis. In survey analyses, marketing researchers must break down free-
response answers to catch mistakes and categorize responses.
3. Share data- With data constructed and free from redundant or unneeded information, it must be
shared with others in the organization. Even though this data is the single version of the truth, it
can be leveraged in different ways.
Steps involved in Data
Discovery
4. Analyze and generate insights- Common tools include distributional analysis,
predictive models, and market basket analysis. It is important to understand the type of
insights generated by different analytical tools.
5. Visualize Insights - Insights need to be communicated once they are found, and
visualizations allow users to easily do this.
Data Discovery - trends
BIG DATA DISCOVERY SMART DATA DISCOVERY
Excel is the base model for data discovery. Its capabilities allows users to pull, prepare and
analyse data within one document. While it can perform all required functions, many tasks
require the manual manipulation of data. The manual and non-customizable nature of
platform severely limits the depth of analysis which can be conducted.
R.
Mostly used by statisticians, R requires a specialised skill set. While the platform is one of
the least user friendly but it is also extremely useful. It is an open-source platform, and it
can explore, edit, analyse and visualize data in many possible ways.
Data Discovery Tools
Qlik Sense, QlikView and Qlik Nprinting
When?
• To show how a one or
more variables change
over time. (Progression)
• connects a series of data
points with a
continuous line.
• Easier to see small
changes, but are less
versatile than bar graphs.
Pie Chart
When?
• To see parts of a whole on a
percentage basis.
• Data visualization professionals
don’t recommend using pie charts.
• Difficult to compare the relative
sizes of areas.
Area Chart
Color- coding
of quantitative data is
commonly called a heat map.
Excel Data
Visualization
Tools
Icon Sets
Each icon represents a range
of values.
Line and
Column
Sparklines
Line sparklines are
clearly useful for time-
series data, while
column sparklines are
more appropriate for
categorical data.
Win-loss
Sparklines
Win-loss sparklines
are useful for data
that move up or
down over time.
American Cancer Society: A case
Study
• The American Cancer Society has been working
for over 100 years to find a cure for cancer and to
help patients fight back, get well, and stay well.
Recency score = 1 point awarded if previous session was within the past seven days
Conversion score = 1 point awarded for each donation, registration for an event or a
view of an entire article on cancer information
Revenue score = 1 point awarded for larger gifts than average gift size of about $70
Insights
Insights
Results
• The new custom metrics allowed the Society’s analysts to identify behavior changes in
each segment that would have otherwise gone unnoticed.
• A separate site called Making Strides Against Breast Cancer is used to raise money
specifically for breast cancer research.
• Analysis showed an Increase in Site performance score in October- Breast Cancer
Awareness Month.
• In response, the Society marketing team created new promotions on Cancer.org to
drive traffic to the Making Strides site. It worked. More than 39,000 people followed
those links throughout the month. The team also created a new donation form on
Cancer.org that sent funds only to breast cancer research. The result was a 5.4%
jump in Cancer.org revenue year over year.
Q&A
Thank You!