Scribd
Upload
11 views19 pages

Customized Lecture 5

Uploaded by

Robert Oo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
11 views19 pages

Customized Lecture 5

Uploaded by

Robert Oo
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 19

Business Intelligence, Analytics, and Data Science: A

Managerial Perspective
Fourth Edition

BDA6123 CUSTOMIZED
LECTURE 5

Diagnostic
Analytics
Slides in this presentation contain
hyperlinks. JAWS users should be
able to get a list of links by using
INSERT+F7

C o p y rig h t© 2 0 1 8 ,2 0 1 4 ,2 0 1 1 P e a rs o n E d u c a tio n ,In c .A lR ig h ts R e s e rv e d


LO1: Correlation

Correlation with Satisfaction


Correlation Coefficient
Lead Time -0.766
Online Order Tracking -0.242
Product Cost 0.097

Diagnostics Analytics: Determine Correlation of Customer Satisfaction

1. Customers forced to wait are unhappy.


2. Those without access to online order tracking are more satisfied.
3. Those who pay more are somewhat happier.
LO2: Regression
Regression: satisfaction constant leadtime cost ol-track
coefficient 192.7338 -6.8856 -1.8025 8.5599
std error of coef 16.1643 0.5535 0.3137 4.0729
t-ratio 11.9234 -12.4391 -5.7453 2.1017
significance 0.0000% 0.0000% 0.0000% 4.0092%
beta-weight -1.0879 -0.4571 0.1586

coefficient of determination 75.03%


total percentage
Diagnostics Analytics: Determine Regression of Customer
Satisfaction
Customers who dislike high cost and forced to wait are
unhappy.
significance more than 0.05 - the data is
.
significance
is important
must less than 0.05 - the data not important
Develop diagnostic Mini-Case
analytics for estimating Oil (Gal) Temp Insulation
heating oil used for a single 275.30
363.80
40
27
3
3
family in January 2022 164.30 40 10
40.80 73 6
based on average 94.30 64 6

temperature and amount 230.90


366.70
34
9
6
6
of insulation. 300.60
237.80
8
23
10
10
121.40 63 3
31.40 65 10
203.50 41 6
441.10 21 3
323.00 38 3
52.50 58 10
Mini-Case
Dependent variable: Gallons Consumed
-------------------------------------------------------------------------------------
Standard T
Parameter Estimate Error Statistic P-Value
--------------------------------------------------------------------------------------
CONSTANT 562.151 21.0931 26.6509 0.0000
Insulation -20.0123 2.34251 -8.54313 0.0000
Temperature -5.43658 0.336216 -16.1699 0.0000
--------------------------------------------------------------------------------------
R-squared = 96.561 percent
R-squared (adjusted for d.f.) = 95.9879 percent
Standard Error of Est. = 26.0138
+
Mini-Case

Y= 562.15 - 5.44x1 - 20.01x2

where: x1 = temperature [degrees F]


x2 = insulation [inches]
Mini-Case
Y = 562.15 - 5.44x1 - 20.01x2

Diagnostic Analytics 1
For a home with zero inches of insulation
and a zero temperature, 562.15 gallons
of heating oil would be consumed.
Mini-Case
Y= 562.15 - 5.44x1 - 20.01x2

Diagnostic Analytics 2
For each incremental increase in
temperature, heating oil consumption
drops 5.44 gallons.
Mini-Case
Y = 562.15 - 5.44x1 - 20.01x2

Diagnostic Analytics 3
For each incremental increase in inches of
insulation, heating oil consumption drops
20.01 gallons.
Mini-Case

Y = 562.15 - 5.44x1 - 20.01x2

with x1 = 15oF and x2 = 10 inches


Diagnostic Analytics 4
Y= 562.15 - 5.44(15) - 20.01(10)
= 280.45 gallons consumed
Mini-Case

R2 = .9656

96.56 percent of the variation in


heating oil can be explained by
the variation in temperature and
insulation.
Mini-Case

R2adj = 0.9599

95.99 percent of the variation in


heating oil consumption can be
explained by the model - adjusted for
number of independent variables and
the sample size
Q1: CORRELATION VERSUS
REGRESSION
1. Correlation makes no a priori assumption and is not concerned
with the relationship between variables.

2. Regression attempts to describe the dependence of 1 response


variable (result) on more than 1 explanatory variables (factors) where
it implicitly assumes that there is a causal effect.
Q2: SIMPLE VERSUS MULTIPLE
REGRESSION
Simple Regression: 1 Factor-> 1 Result
Quantity (explanatory variable) and Price (response variable)

Multiple regression: Multiple Factors -> 1 Result


Personal characteristics (e.g.,Income, gender, ethnicity) to predict the
purchase
Q3: How Do We Know If the Model Is
Good Enough?
• Good R2 values would usually come close to one, whereas an R2
value of 0.3-0.7 may be considered as a good-enough fit.

Increase R2 value
1. Adding more explanatory variables,
2. Taking some of the variables out of the model, or
3. Using different data transformation techniques
LO3: Data Mining
• Data Mining is:
(1) The efficient discovery of previously unknown, valid,
potentially useful, understandable patterns in large datasets

(2) The analysis of (often large) observational data sets to find


relationships and to summarize the data in novel ways that
are both understandable and useful to the data owner
LO3: Data Mining

Association Data Mining

buys( “computer”) => buys( “software”)


[confidence = 50%]

If a customer buys a computer, there is a 50%


chance (confidence) that she will buy software.

Data Mining: Concepts and Techniques


LO3: Association Data Mining
Support = frequency of buying the products

Confidence >=0.5 shows Product 1 and Product 2 are suitable to be


sold as a package.

Lift >=1 indicates the suitability to produce Product 1 and Product 2


together.
LO3: Association Data Mining- Examining Market
Demand

1. HelloFresh’s team uses geographic location, demographic data,


meal type, flavor preferences, and order timing to identify
relationships between trends in market demand.

2. Imagine the HelloFresh team identifies a spike in fish-based recipe


orders. After conducting diagnostic analysis, they find that the
attributes most highly correlated with ordering fish recipes are
identifying as female and living in the North Malaysia.

You might also like