1|Page
ISYE 6501 MIDTERM EXAM (2025/2026): PROGRESSIVE
ASSESSMENT WITH DETAILED EXAM QUESTIONS AND
CORRECT ANSWERS
Tree ......answer.....Iterative split (branching) of a data set into
more-specific subsets that each are modeled separately. Often
used for classification, regression, and decision-making. Also
can be used to solve optimization problems.
Trend ......answer.....Increase or decrease in data values over
time.
Triple exponential smoothing ......answer.....Three-parameter
exponential smoothing technique that incorporates trend and
seasonality; also called Winters' method or Holt-Winters.
,2|Page
Stationary process ......answer.....Process whose joint
probability distribution and statistical properties (mean, variance,
autocorrelation, etc.) do not vary with time. Examples include
data with trends or cycles.
Steady state ......answer.....In a Markov chain, having the same
probability distribution of being in each state, before and after a
transition.
Step size ......answer.....Distance to move in an improving
direction, to get to a new solution given a current solution and
an improving direction.
Stepwise regression ......answer.....Variable selection process
that can combine forward selection and backward regression.
,3|Page
Stochastic dynamic program ......answer.....Dynamic program
where the outcome of one or more decisions is determined
according to probabilities.
Stochastic optimization ......answer.....An optimization model
that accounts for randomness or uncertainty.
Stochastic simulation ......answer.....Simulation that includes
randomness/uncertainty, so results can be different each run.
Structured data ......answer.....Data that is highly organized, so it
can be searched, queried, and analyzed easily - for example, a
table with the name, age, and country of participants in this
course.
, 4|Page
Sum-of-squared errors ......answer.....Sum of the squares of all
the differences between data and model output. In regression,
this is a measure of variance.
Supervised learning ......answer.....Machine learning where the
"correct" answer is known for each data point in the training set.
Support vector ......answer.....In SVM models, the closest point
to the classifier, among those in a category.
Support vector machine (SVM) ......answer.....Classification
algorithm that uses a boundary to separate the data into two or
more categories ("classes").
SVM ......answer.....Support vector machine.
ISYE 6501 MIDTERM EXAM (2025/2026): PROGRESSIVE
ASSESSMENT WITH DETAILED EXAM QUESTIONS AND
CORRECT ANSWERS
Tree ......answer.....Iterative split (branching) of a data set into
more-specific subsets that each are modeled separately. Often
used for classification, regression, and decision-making. Also
can be used to solve optimization problems.
Trend ......answer.....Increase or decrease in data values over
time.
Triple exponential smoothing ......answer.....Three-parameter
exponential smoothing technique that incorporates trend and
seasonality; also called Winters' method or Holt-Winters.
,2|Page
Stationary process ......answer.....Process whose joint
probability distribution and statistical properties (mean, variance,
autocorrelation, etc.) do not vary with time. Examples include
data with trends or cycles.
Steady state ......answer.....In a Markov chain, having the same
probability distribution of being in each state, before and after a
transition.
Step size ......answer.....Distance to move in an improving
direction, to get to a new solution given a current solution and
an improving direction.
Stepwise regression ......answer.....Variable selection process
that can combine forward selection and backward regression.
,3|Page
Stochastic dynamic program ......answer.....Dynamic program
where the outcome of one or more decisions is determined
according to probabilities.
Stochastic optimization ......answer.....An optimization model
that accounts for randomness or uncertainty.
Stochastic simulation ......answer.....Simulation that includes
randomness/uncertainty, so results can be different each run.
Structured data ......answer.....Data that is highly organized, so it
can be searched, queried, and analyzed easily - for example, a
table with the name, age, and country of participants in this
course.
, 4|Page
Sum-of-squared errors ......answer.....Sum of the squares of all
the differences between data and model output. In regression,
this is a measure of variance.
Supervised learning ......answer.....Machine learning where the
"correct" answer is known for each data point in the training set.
Support vector ......answer.....In SVM models, the closest point
to the classifier, among those in a category.
Support vector machine (SVM) ......answer.....Classification
algorithm that uses a boundary to separate the data into two or
more categories ("classes").
SVM ......answer.....Support vector machine.
