Download docx

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Bayesian inference in marketing wikipedia , lookup

Transcript
CSIS-114: Final Exam Review
The final exam will include 75 questions with the same general format of the first
two exams. It will include mostly T/F, multiple-choice, and fill-ins.
About 7-9 questions will have open-ended short paragraph answers (2-4 sentence
responses).
25 questions will be taken from Exam 1
25 questions will be taken from Exam 2
8 questions will pertain to student presentations
Customer Relationship Management
Role of Social Networking System in Marketing
Basics of Accounting Systems
Google Docs (cloud computing concept) vs.
Microsoft Office (installed software)
Women in IT
Artificial Intelligence in Business
It is recommended that you view and read your classmates websites
(see the links on the Schedule)
8 questions will come directly from the Chapter 8 and Chapter 9 lectures.
It is recommended that you read Chapter 8 and 9 and review the Power Point
presentations
(see the links on the Schedule)
9 questions will come directly from the Market Basket, SCM, Fund Trading and
Pivot chart labs. Be prepared to compare and contrast these labs with previous labs,
namely the WageMart and Excel lab.
(see the lab review sheet)
Lab Review
SCM Lab (RFID + XML)
RFID - a great example of a hardware technology that gives a company a strategic
advantage



What is an RFID chip?
What is the chip’s role in Supply Chain Management
Hints:
o RFID allows items to be uniquely identified (ID number)
o Superior alternative to Bar Code stickers
XML - a great example of information/software technology






What is an XML document?
How can XML be used with RFID chips?
What is the document’s role in Supply Chain Management
Tags add context to data: <context> Data </context>
XML can encode everything from a Purchase Order to Web Page
XML is standardized and robust; What does this mean?
Market Basket Analysis - example of Data Mining
Support: Probability (P) that an item is in someone’s checkout basket
A,B,E
C,D
A,B,F
C,D,G
A,B
E,F,G
A,B,F,G
E,F
A,D,F
E,G
P(A) = 5/10 = 50%
P(AB) = 4/10 = 40%
P(C) = 2/10 = 20%
P(CD) = 2/10 = 20%
Confidence X  Y = P(XY)/P(X) : If item X is purchased, what is the
probability that item Y is also purchased
Confidence B  A
Confidence C  D
= P(AB)/P(A) = 40%/50% = 80%
= P(CD)/P(C) = 20%/20% = 100%
Quality X  Y = Confidence X  Y * P(YX) : High quality association rules
Quality A B
Quality C D
= 80% * 40%
= 100% * 20%
= 32%
= 20%
Apriori Algorithm: Enables the calculation of high quality, confident
association rules given billions of transactions and thousands of items

Without the Apriori Algorithm, the calculation would take too long
(millions of years).

How it works: By setting minimum support level, the algorithm can
prune low confidence pairs (2-itemsets) to compute 3-itemsets. Then,
the pruned 3-itemsets can compute 4-itemsets. The algorithm is
guaranteed to return all the itemsets above the minimum support
level.

When you get to 5-, 6-, or 7-itemsets, the pruning reduces the number
of possible sets from trillions to a few thousand or hundred, which can
help humans discover very complex, high quality association rules.
Complex Rule Example ADGMS  CLPT, i.e., 5 items (A,D,G,M, and S) imply
with great confidence that 4 items (C, L, P, and T) are purchased.
Pivot Chart Lab - Great example of Online Analytical Processing




Slice/view data by dimension
Drill down to smaller and smaller data sets
Allows lots of data to be summarized and analyzed by human interaction
Online means Real-time and Interactive, not on the web
Artificial Intelligence for Business


We used OLAP to confirm patterns, we encoded the patterns as IF statements
to predict future cases. The spreadsheet can automate the human decision
making process on a large scale, faster than a human.
Such a system enables timely, accurate predictions without a human
decision-maker (Business Intelligence System)
OLAP (Pivot Chart Lab) vs. Data Mining (Market Basket Lab)
OLAP – a hypothesis, human intelligence, and interactive analysis tools drive the
pattern finding process
Example: A marketer thinks that geography plays a role in sales; a Pivot
chart shows that Southern stores have better sales. The hypothesis can come
before the data and the data helps to confirmed the hypothesis.
Data Mining – An algorithm (Apriori, pattern matching, etc.) drives the pattern
finding process. After patterns are found human intelligence can derive a
hypothesis.
Example: The Apriori algorithm discovers a high quality association rule
(Beer  Diapers). Later, Marketers try to unravel the reason why. The data
analysis must come before the hypothesis because the data is to big for
humans to analyze. You see this in Market Basket, Genomic, and Network
analysis.
Fund Trading Lab (Decision Support Automation)
Another Example of Business intelligence: Using a Database to compute the optimal
sequence of trades.



At first we use a graph and human intuition to make the trades
We do better if we use a query to calculate and sort all possible transactions
We use Database tools to pick the best one’s that don’t overlap
Contrast to Wagemart (Decision Support Summarizing)
 In Wagemart, we start with tons of data (individual salaries, availability) and
reduce it to simple info (total cost, average rating) to help make a decision.
 In Fund Trading, we start with less data and compute every possible
transaction
 Both system help model scenarios to compute the outcome of decisions, but
one is structured (one scenario to optimize) and the other unstructured
(many different scenarios to consider).
o Wagemart was very unstructured, many different ways to cut costs.
o Fund Trading was more structured, i.e., you can only buy and sell and
you just have to decide the optimal time and funds to buy/sell.