ISYE 6501 FINAL UPDATED ACTUAL QUESTIONS WITH
CORRECT ANSWERS
Question 1.
k-fold cross validation
ANSWER
Validation Technique where data is divided into X number of data subsets. Each subset is then
used as a for testing while the rest are used for training. The algorithm then rotates through
each subset and averages the results
Question 2.
Non-parametric tests
ANSWER
useful when- we don't know much about the form of the underlying distribution the data
comes from/ it doesn't fit a nice distribution, it's important to have information about the
median, we don't have much data
Question 3.
neural networks
ANSWER
Machine learning method comprised of three levels: input level, hidden level, and output level.
Each level of nodes receives it input from the previous layer, calculates function of weighted
inputs, gives its output to the next layer, then uses its error to adjust its weighted functions.
Question 4.
Optimization
ANSWER
Prescriptive analytic tool comprised of three main components. Variables, constraints, and
objective function.
, Question 5.
Bayesian modeling
ANSWER
Based on Bayes' theorem, it is used to estimate the conditional probability of a given data
point belonging to a particular class using a probabilistic approach for data classification and is
based on the assumption that attributes in the training examples are governed by probability
distributions.
Question 6.
Bernoulli Distribution
ANSWER
-a distribution of a single Binary event, has two possible outcomes where the positive is p and
the negative is 1-p
Question 7.
PCA Pros and
Cons
ANSWER
Pros: Removes correlated features
Can improve algorithm performance by omitting correlated variables
Reduces over fitting
Improves visualization
Cons: Harder to interpret effects of individual independent variables
Requires data standardization
Question 8.
CUSUM
ANSWER
Change detection model that keeps a running total of the amount that observations vary
above the expected value. The running total exceeds a preset threshold value, it indicates there
has been a change.
CORRECT ANSWERS
Question 1.
k-fold cross validation
ANSWER
Validation Technique where data is divided into X number of data subsets. Each subset is then
used as a for testing while the rest are used for training. The algorithm then rotates through
each subset and averages the results
Question 2.
Non-parametric tests
ANSWER
useful when- we don't know much about the form of the underlying distribution the data
comes from/ it doesn't fit a nice distribution, it's important to have information about the
median, we don't have much data
Question 3.
neural networks
ANSWER
Machine learning method comprised of three levels: input level, hidden level, and output level.
Each level of nodes receives it input from the previous layer, calculates function of weighted
inputs, gives its output to the next layer, then uses its error to adjust its weighted functions.
Question 4.
Optimization
ANSWER
Prescriptive analytic tool comprised of three main components. Variables, constraints, and
objective function.
, Question 5.
Bayesian modeling
ANSWER
Based on Bayes' theorem, it is used to estimate the conditional probability of a given data
point belonging to a particular class using a probabilistic approach for data classification and is
based on the assumption that attributes in the training examples are governed by probability
distributions.
Question 6.
Bernoulli Distribution
ANSWER
-a distribution of a single Binary event, has two possible outcomes where the positive is p and
the negative is 1-p
Question 7.
PCA Pros and
Cons
ANSWER
Pros: Removes correlated features
Can improve algorithm performance by omitting correlated variables
Reduces over fitting
Improves visualization
Cons: Harder to interpret effects of individual independent variables
Requires data standardization
Question 8.
CUSUM
ANSWER
Change detection model that keeps a running total of the amount that observations vary
above the expected value. The running total exceeds a preset threshold value, it indicates there
has been a change.
