Transcript Business Analytics

Business Intelligence
and Data Mining
Session 14 Section 3
Instructor: Michael Sutton, PhD, CMC, AdmA, MIT
EMBA 512
Fall 2015
Business Analytics
Online analytical processing (OLAP) is multidimensional data analysis that is
initiated by a business user and consists of complex reporting mechanisms,
analyses, and data visualization
—Codd et. al. (1993), Providing OLAP (On-line Analytical Processing) to UserAnalysts: An IT Mandate
Boise State Executive MBA Program Fall 2015
2
 Biz Analytics—Hot Topic
 BIG Data—What is It?
 Biz Analytics—Where did They Come From?
 Biz Analytics—What are They Like Now?
Agenda
 Biz Analytics: Core Principles
 Types of Biz Analytics






Data Quality Analytics
Descriptive Analytics
Diagnostic Analytics
Prescriptive Analytics
Predictive Analytics
Semantic Analytics
Boise State Executive MBA Program Fall 2015
3
http://www.informationbuilders.es/intl/co.uk/presentations/four_types_of_analytics.pdf
QUIZ:
What do Beer
and Business
Analytics Have
in Common?
Boise State Executive MBA Program Fall 2015
4
http://blueharbors.com/demand-analytics-software-continue-2017/
Why Are
Business
Analytics Such
a HOT Topic?
[1]
Boise State Executive MBA Program Fall 2015
5
https://oneragingbull.wordpress.com/
Why Are
Business
Analytics Such
a HOT Topic?
[2]
Boise State Executive MBA Program Fall 2015
6
http://www.slideshare.net/smongeau1/acfe-presentation-on-fraud
Why Are
Business
Analytics Such
a HOT Topic?
[3]
Boise State Executive MBA Program Fall 2015
7
VERACITY
BIG DATA:
What is It? [1]
Boise State Executive MBA Program Fall 2015
http://med.cornell.libguides.com/HINF5008
VIABILITY
8
Data in
Motion
BIG DATA:
What is It? [2]
Data
Usefulness
Data in
Many
Forms
http://www.patrickcheesman.com/how-big-data-cantransform-your-understanding-of-your-customers/
Data at
Scale
Data
Uncertainty
Boise State Executive MBA Program Fall 2015
9
 “Data. Data. Data. I cannot make bricks without clay!”
 1989, Erik Larson, author of “The Devil in the White City” and “In The
Garden of Beasts,” wrote a piece for Harper’s Magazine, which was
reprinted in The Washington Post:
BIG DATA:
Where Did It
Come From?
[1]
 Conclusion: “The keepers of big data say they do it for the consumer’s
benefit. But data have a way of being used for purposes other than
originally intended.”
 “The term Big Data, which spans computer science and
statistics/econometrics, probably originated in the lunch-table
conversations at Silicon Graphics in the mid-1990s, in which John
Mashey figured prominently.”
 —Diebold, F. X., Cheng, X., Diebold, S., Foster, D., Halperin, M., Lohr, S.,
... & Shin, M. (2012). A Personal Perspective on the Origin (s) and
Development of “Big Data”: The Phenomenon, the Term, and the
Discipline. (Working Paper). Retrieved from:
 http://www.ssc.upenn.edu/~fdiebold/papers/paper112/Diebold_Big_Data.p
df
 See: Press, G. (May 9, 2013). A Very Short History Of Big Data. Forbes.
 http://www.forbes.com/sites/gilpress/2013/05/09/a-very-short-history-ofbig-data/
Boise State Executive MBA Program Fall 2015
http://www.mblast.com/marketing-return-on-investment/big-data-social-lead-discovery/
 Sherlock Homes and the Etymology of the ‘Big Data’ Case
10
http://www.healthcareimc.com/node/727
Business
Analytics:
Where Did It
Come From?
[2]
Boise State Executive MBA Program Fall 2015
11
http://www.slideshare.net/smongeau1/acfe-presentation-on-fraud
Business
Analytics:
What’s It Like
Now?
Boise State Executive MBA Program Fall 2015
12
Business
Analytics Core
Principles:
ADHD-RAT
G IV E F
 Analyze, Discover, Haggle, and Decide (ADHD) upon an
appropriate action, based on information that is:
 Relevant
 Actionable
 Timely
 Graph all metrics.
 Interact with information at the speed of business.
 Visualize data to highlight information patterns.
Exercise 4:
5 min.
 Exercise gut feelings and intuition through simulation
 Forecast by enhancing visual patterns.
Surma (2011), Case Study 2.1, (p. 27-32), Alpha Chain Stores:
demonstrated business requirements analysis
and proposed solution approach
Boise State Executive MBA Program Fall 2015
13
What are the 6
Types of
Business
Analytics? [1]
Boise State Executive MBA Program Fall 2015
14
http://sctr7.com/2014/07/09/twelve-emerging-trends-in-data-analytics-part-1-of-4/
What are the 6
Types of
Business
Analytics? [2]
Boise State Executive MBA Program Fall 2015
15
http://digitalmarketingstrategy.ucd.ie/data-analysis-marketing-making-data-relevant/
Data Quality
Business
Analytics [1]
Boise State Executive MBA Program Fall 2015
16
 Data Quality: a perception or an assessment of the fitness of data
to serve its purpose within a given context. Characteristics/Metrics
of data quality include:
Data Quality
Business
Analytics [2]








Accessibility
Accuracy
Appropriate presentation
Completeness
Consistency across data sources
Update status
Relevance
Reliability
Boise State Executive MBA Program Fall 2015
17
https://tdwi.org/articles/2012/05/01/feature-ten-goals-for-next-generation-data-quality.aspx
Data Quality
Techniques
Boise State Executive MBA Program Fall 2015
18
Decision Management Solutions - From Business Intelligence to Predictive Analytics
http://www.slideshare.net/jamet123/from-business-intelligence-to-predictive-analytics
Descriptive
Business
Analytics [1]
http://whybinoexcuses.com/2015/03/09/moving-fromdescriptive-to-predictive-analytics-with-big-data/
http://www.collings.co.za/2011/07/message-over-media.html
Boise State Executive MBA Program Fall 2015
19
Descriptive
Business
Analytics [2]
 looks at data and analyzes past
events for insight as to how to
approach the future.
 looks at past performance and
understands that performance
by mining historical data to look
for the reasons behind past
success or failure.
 Almost all management
reporting such as sales,
marketing, operations, and
finance, uses this type of postmortem analysis.
Boise State Executive MBA Program Fall 2015
Descriptive models/tools:
 quantify relationships in data in a way
that is often used to classify
customers or prospects into groups
related to products and services.
 can be used, for example, to
categorize customers by their product
preferences and life stage.
 can be utilized to develop further
models that can simulate large
number of individualized agents and
make predictions.
 For example, descriptive analytics
examines historical electricity usage
data to help plan power needs and
allow electric companies to set
optimal prices.”
http://www.rosebt.com/blog/descriptive-diagnostic-predictive-prescriptive-analytics
Descriptive analytics:
20
Diagnostic
Business
Analytics [1]
Boise State Executive MBA Program Fall 2015
http://www.clickz.com/clickz/column/2323767/getting-started-with-real-time-analytics
https://www.andertoons.com/business/cartoon/4619/i-think-i-speakfor-all-of-us-when-i-say-what-in-gods-name-are-you-talking-about
21
Diagnostic
Business
Analytics [2]
 used for discovery or to
determine why something
happened.
 For example, for a social
media marketing
campaign, you can use
diagnostic analytics to
assess the number of posts,
mentions, followers, fans,
page views, reviews, pins,
etc.
 Thousands of online
mentions that can be
distilled into a single view
to see what worked in your
past campaigns and what
didn’t.
Boise State Executive MBA Program Fall 2015
 Ask specific questions:
 “Where should we look?”
(Discovery/Alerts)
 “Why did it happen?”
(Query/Drill down)
http://www.ingrammicroadvisor.com/data-center/fourtypes-of-big-data-analytics-and-examples-of-their-use
 Diagnostic analytics:
22
http://www.informationbuilders.es/intl/co.uk/presentations/four_types_of_analytics.pdf
http://www.equest.com/category/cartoons/cartoons-2013/
Predictive
Business
Analytics [1]
http://www.opsrules.com/supply-chain-optimization-blog/topic/analytics
Boise State Executive MBA Program Fall 2015
23
Predictive
Business
Analytics [2]





must be executable at a decision point
action/events likely to happen
Identify past patterns to predict the future
turns data into valuable, actionable information.
uses data to determine the probable future outcome of an event or a
likelihood of a situation occurring.
 encompasses a variety of statistical techniques from modeling,
machine learning, data mining and game theory that analyze
current and historical facts to make predictions about future events.
 For example, some companies use predictive analytics for the entire
sales process, analyzing lead source, number of communications,
types of communications, social media, documents, CRM data, etc.
 Ask specific questions:
 “What will happen next” (Predictive Modeling)
 “What is the pattern?” (Statistical Modeling)
Boise State Executive MBA Program Fall 2015
http://www.rosebt.com/blog/descriptive-diagnostic-predictive-prescriptive-analytics
 Predictive Analytics:
24
http://www.kdnuggets.com/2014/12/cartoonunexpected-data-science-recommendations.html
Prescriptive
Business
Analytics [1]
http://www.allanalytics.com/author.asp?
section_id=1859&doc_id=277140
Boise State Executive MBA Program Fall 2015
25
 Prescriptive Analytics:
Prescriptive
Business
Analytics [2]
 automatically synthesizes big data, mathematical sciences, business
rules, and machine learning to make predictions and then suggests
decision options to take advantage of the predictions.
 goes beyond predicting future outcomes by also suggesting actions
to benefit from the predictions and showing the decision maker the
implications of each decision option.
 suggests decision options on how to take advantage of a future
opportunity or mitigate a future risk and illustrate the implication of
each decision option.
 provides a laser-like focus to answer specific questions.
 In practice, prescriptive analytics can continually and automatically
process new data to improve prediction accuracy and provide better
decision options.
 Ask specific questions:
 “What is the best action?” (Optimization)
 “What if we try this?” (Random Testing)
Boise State Executive MBA Program Fall 2015
26
https://s-media-cacheak0.pinimg.com/736x/1f/dc/bb/1fdcbb
4964fe7b7824d09e3e4aa0a6b7.jpg
Semantic
Business
Analytics [1]
https://metaeconomics.wordpress.com/
Boise State Executive MBA Program Fall 2015
27
Semantic
Business
Analytics [2]
 a semantic knowledge model is a way to abstract disparate data and
information, from linked, unstructured and structured data.
 knowledge modeling is about describing what data means and where it fits.
 we more easily understand and abstract knowledge. Consequently it helps us
to understand how different pieces of information relate to each other.
 Uses links between IP Address nodes to build patterns, relationships, and
meaning through the application of an Ontology concepts (controlled
vocabulary) and Taxonomy of terms (BT, NT, RT, SN)
 For example, portfolio modeling in the financial services sector:
 Cannot simply analyze past performance
 Must take into account external indicators, political events or unrest, currency
issues —impact company stock price.
 Need an underlying infrastructure that caters for dynamic changes to interrelated
knowledge relevant to the portfolio.
 Ask specific questions:
 “Why is this possible?”
 “What does this mean?” (Random Testing)
http://sparklingspur.com/all-about-appleiphone-4s-features-full-specification-and-price/
Boise State Executive MBA Program Fall 2015
https://fbhalper.wordpress.com/2007/11/29/whats-a-semantic-model-and-why-should-we-care/
 Semantic Analytics:
28
http://daselab.cs.wright.edu/pub/2013-02-Siemens-BIGDATA.pdf
Semantic
Business
Analytics [3]
Boise State Executive MBA Program Fall 2015
29
http://daselab.cs.wright.edu/pub/2013-02-Siemens-BIGDATA.pdf
Semantic
Business
Analytics [4]
Boise State Executive MBA Program Fall 2015
30
http://daselab.cs.wright.edu/pub/2013-02-Siemens-BIGDATA.pdf
Semantic
Business
Analytics [4]
Boise State Executive MBA Program Fall 2015
31
http://lod-cloud.net/state/
Semantic
Business
Analytics [5]
Boise State Executive MBA Program Fall 2015
32
https://onthegocio.wordpress.com/2
013/05/06/big-data-offers-no-value/
Boise State Executive MBA Program Fall 2015
http://blogs.position2.com/web-3-0-the-new-interactive-world
http://www.informationbuilders.es/intl/co.uk/presentations/four_types_of_analytics.pdf
Pause?
33
Section 3
Recap
Boise State Executive MBA Program Fall 2015
34