Data Analytics- Quiz 1
a stack of DVDs as tall as a 55-story building
1 petabyte is equivalent to what?
the storage capacity of NASA datacenter
1 yottabyte is equivalent to what?
1. Volume 2. Variety 3. Velocity
3 V's of Data Analytics
unstructured
80%-90% of future data growth comes from ____________ data types
1 byte
Basic unit of measurement
What happened?
Descriptive analytics answers what question?
Why did it happen?
Diagnostic analytics answers what question?
1. the use of database marketing and decision-science-based analytical tools 2. deliver great service that customers demand
How has Harrah increased customer loyalty in this challenging economy?
databases
It mostly involves data stored in ________.
structured data
Most traditional analysis performed in companies includes _____ _____.
unsupervised learning
No target attribute
What will happen?
Predictive analytics answers what question?
How can we make it happen?
Prescriptive analytics answers what questions?
structured data
Transaction data and spreadsheets are examples of what?
1. Nominal 2. Ordinal
Two types of data under categorical
1. Descriptive 2. Diagnostic 3. Predictive 4. Prescriptive
Types of Data Analytics:
1. Numerical 2. Categorical
Types of data:
1. computers have become more powerful 2. networking has become ubiquitous 3. algorithms have been developed that can connect multiple data sets
What contributed to the opportunities to perform data analytics?
Instead of focusing on how much people spent in our casinos during a single visit, it became clear that they needed to focus on their potential worth over time.
What did Harrah learn from the data they collected?
It created a large customer database that included information about how customers behaved and their spending patterns.
What did the Total Gold player card program do that was good?
A focus on customer satisfaction
What other important aspect, combined with deep data mining and decision-science marketing, helped Harrah's over strategy?
prescriptive
What type of data analytics is for decision support and decision automation?
prescriptive
What type of data analytics is more for optimization?
prescriptive
What type of data analytics requires no human input?
descriptive
What type of data analytics requires the most amount of human input?
1. Harrah's revenue depended on their casinos 2. cultivating lasting relationships with the company's core customers—slot players—would lead to greater and more sustainable profit growth
What was Harrah's thought behind their idea and success?
1. nothing differentiated this program from their competitor's effort 2. customers earned different rewards at different properties 3. customers were not given any incentives to consolidate their gaming with Harrah's
What were the problems behind the Total Gold player card program?
1,800 ZB
all the data recorded in 2011 was equivalent to how many zettabytes?
5 EB
all the information generated in 2003 is equal to how many Exabytes?
regression
an attempt to predict a continuous attribute
uni-variable
bar charts and histograms- uni-variable or bi-variable?
structured data
data containing a defined data type, format, and structure
unstructured data
data that has no inherent structure, which may include text documents, sensor data, images, audio, video, log files
ordinal
data that has order
ordinal data
data that includes relative frequency
nominal data
data that is in counts are included in a bar chart
nominal
data with no order
supervised learning
discover patterns in the data that relate data attributes with a target (class) attribute
Veracity
errors in data
clustering
finds "natural" grouping of instances given un-labeled data
1 GB
how many gigabytes is a two-hour film?
30 KB
how many kilobytes is one page of text?
5 MB
how many megabytes is a piece of music?
1 TB
how many terabytes is 6 million books?
classification
learns a method for predicting the instance class from pre-labeled (classified) instances
bi-variable
line plots and scatterplots- uni-variable or bi-variable?
Association Rules
method for discovering interesting relations between variables in large databases
1. supervised learning 2. unsupervised learning
methods of business analytics
1. classification 2. regression
methods of supervised learning
1. clustering 2. association rules
methods of unsupervised learning
measurable
numerical data is _________
velocity
refers to the increasing speed of which data is created and the speed at which it can be processed, stored, and analyzed
True
structured data can contain unstructured components. True or False?
unstructured data
text documents (tweets, facebook), sensor data, images, audio, video, and log files are examples of what?
Business Analytics
the study of data through statistical and operations analysis, the formation of predictive models, application of optimizations techniques and the communication of these results to customers, business partners and colleague executives
1. byte 2. Kilobyte 3. Megabyte 4. Gigabyte 5. Terabyte 6. Petabyte 7. Exabyte 8. Zettabyte 9. Yottabyte
volumes of data
classification
we try to predict a categorical value with __________
regression
we try to predict numerical variable with __________
expand their business in other emerging markets and focusing on the corporation's gaming.
what did Harrah do that was different than their competitors?
beer
what did Walmart find, after data mining, was the top-selling pre-hurricane item?
class setting
what is an example of supervised learning?
nominal or ordinal
what kind of data can be made into bar charts?
numerical
what kind of data can be made into histograms?
numerical
what kind of data can be made into line plots and scatterplots?
prescriptive
what type of data analytics has the most value?
prescriptive
what type of data analytics is most difficult
1. Total Gold player card program
what was Harrah's first tactic in building customer relations?
uni-varied
when there is one variable in the chart