Week 3 Flashcards
Domain Experts
needed to frame a problem properly in a way that will provide value to the organization
Data/Database Experts
needed to identify what data is available for predictive modeling and how that data can be accessed and normalized.
Predictive Modeling Experts
needed to build the models that achieve the business objectives.
Unit of Analysis
problem specific and therefore is defined as part of the business understanding stage of predictive modeling.
Target Variable
a column in the modeling data that contains the values to be estimated or predicted as defined in the business objectives.
Predictive Analytics
forecasts what might happen.
Descriptive Analysis
explains what happened.
Measures of Accuracy
used if the purpose of the model is to provide highly accurate predictions or decisions to be used by the business.
Classification Problem
use Percent Correct Classification.
Percent Correct Classification
measures overall accuracy without regard to what kind of errors are made; every error has the same weight.
Confusion Matrix
enumerates different ways errors are made, like false alarms and false dismissals.
R squared, average error, Mean Squared Error(MSE), median error, average absolute error and median absolute error
metrics used for assessing models in continuous-valued estimation problems.
Stakeholder Analysis Worksheet
questions that must be answered with a “yes” in order for the project to start well from the beginning.
ABT (Analytical Base Table)
constructed in response to a business problem. Properly represents the characteristics of a prediction subject.
Business Objectives
a company’s problem they hope to mitigate or get rid off. Data scientists need to understand the objective to know what to achieve or accomplish.
