Exam Name TRUE/FALSE. Write T if the statement is true and 'F' if the statement is false. 1) A confusion matrix shows just the predicted classifications at a glven threshold value. 1) 2) Pruning a decision tree will sharpen the model's predictive powers. 2) 3) 3) The closer Recelver-Operating-Characteristic (ROC) curve comes to the 45-degree diagonal of the ROC space (chart), the less accurate the test. 4) 1) Calculation of a mean, median and mode on a new data set could be an activity of an overall exploratory analysis as part of a management accountant's role of obtaining and exploring relevant data while working a data analytics process. 5) 5) A binary outcome implies there are more than two possiblc outcomes to a certain siluation such as a revenue that can produce a profit, a loss, or equal expenses. 6). 6) The Receiver-Operating-Characteristic curve plots the true positive rate on the x-axis and the false positive rate on the y-axis. 7) 7) The concept of deployment in data science refers to the application of a model for prediction using a new data, 8) A) Gini Impurity is the probability of incorrectly classifying a randomly chosen element in the dataset if it were randomly labeled according to the class distribution in the dataset 9) A targot variable is a value to be predicted by a model that utilizes feature variables 9) 10) The Image of visualization of a decision tree is a serles of decision nodes and connecting lines. 10) 11) Numeric analysis is a lype of exploratory data analysis. 11) 12) 12) In Carrying out the data science framework, dala leakage happens when some data is inappropriately disclosed external parties 13) The decision tree algorithm simply prepares a linear regression. 13) 14) 14) When building a decision tree, you use each attribute to answer a question. The answer to each question decides the next question. 15) 15) Predictive modeling is a data science technique used to make Estimates based on past or current data. 16) 16) A listing of descriptions of the dala altribules of a datasct is called a data index and is a reference for both data base administrators and analysts who are building decision support models. 17) A logistic regression model to estimate the relationship between independent featurc variables and the target variable would result in a straight-line fit through a through a scatter plot of data points. 17) 18) Cross Valldation techniques allows you to alternate between training and testing an algorithm. 18) 19) Both a ROC Curve and a decision tree can help a manager visualize the performance of a model by identifying the tradcoff between false positives and truc positives. 19) 20) Algorithmic models "learn from the feedback of experts. 20)