GT Students and Verified. All Questions with accurate ansswers, Graded A+ 2022 predictor

Document Content and Description Below

GT Students and VeriÕed View the Proctoring System Requirements to ensure that your set-up will work. Note that proctoring is only supported on MacOS and Windows machines. We recommend 2 GB of fre ... e space on your machine, and a functioning Webcam is required. Your space should be clean, no writing visible on walls or surfaces, and you should be alone in the room. Please make sure that you have veriÕed your ID before taking the exam. 95 Minute Time Limit Instructions Work alone. Do not collaborate with or copy from anyone else. You may use any of the following resources: One sheet (both sides) of handwritten (not photocopied or scanned) notes If any question seems ambiguous, use the most reasonable interpretation (i.e. don't be like Calvin):   3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 2/26 Good Luck! Question 0 -- Practice with Drag & Drop 0 points possible (ungraded)  Keyboard Help Some of the quiz questions are Drag-and-Drop. You'll need to drag one or more answers to a location. Some answers might not be used at all, and some answers will be used once. To get full credit you might need to drag more than one answer to some locations, just one answer to other locations, and some locations might not have any correct answers. Please do this quick practice question. The question will give you feedback to make sure you've done it correctly, but the real quiz questions will not. x=1,y=7 x=2,y=3 x=1,y=43/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 3/26 FEEDBACK  Correctly placed 3 items.  Good work! You have completed this drag and drop problem. Note that: (1) There are two places you could've put (x=2,y=3); either one would be correct. (2) One location (x+y=2) had nothing dragged to it. Another location had two answers dragged to it. (3) One choice (x=1,y=7) was not dragged anywhere, since it wasn't correct for anything. You have used 1 of 10 attempts.  Reset Submit  Show Answer Question 1 9/13 points (graded)  Keyboard Help Drag each of the 13 models/methods to one of the 5 categories of question it is commonly used for, unless no correct category is listed for it. For models/methods that have more than one correct category, choose any one correct category; for models/methods that have no correct category listed, do not drag them. x=1,y=6 Principal component analysis3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 4/26 FEEDBACK  Correctly placed 8 items.  Misplaced 4 items.  Good work! You have completed this drag and drop problem. You have used 1 of 1 attempts.  Show Answer Submit  Reset CART k-nearest-neighbor Random forest k-means Linear regression Logistic regression Support vector machine ARIMA Cross validation CUSUM Exponential smoothing GARCH3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 5/26 Question 2 3.0/3.0 points (graded) Select all of the following models that are designed for use with attribute/feature data (i.e., not time-series data):  You have used 1 of 1 attempt  Final attempt was used, highest score is 9.0 k-nearest-neighbor Support vector machine Random forest GARCH Logistic regression Principal component analysis Exponential smoothing Linear regression CUSUM ARIMA k-means Submit3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 6/26 Information for Questions 3a, 3b, 3c Figures A and B show the training data for a soft classiÕcation problem, using two predictors (x and x ) to separate between black and white points. The dashed lines are the classiÕers found using SVM. Figure A uses a linear kernel, and Figure B uses a nonlinear kernel that required Õtting 16 parameter values. Figure A Figure B Question 3a 3.0/3.0 points (graded) 3a. Select all of the following statements that are true. 1 2 Figure A's classiÕer is based only on the value of x1 . Figure A's classiÕer is more likely to be over-Õt than Figure B's classiÕer. Figure A's classiÕer has a narrower margin than Figure B's classiÕer in the training data.3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 7/26  You have used 1 of 1 attempt Question 3b 2.25/3.0 points (graded) 3b. Select all of the following statements that are true.  You have used 1 of 1 attempt Question 3c 3.0/3.0 points (graded) Figure A's classiÕer incorrectly classiÕes exactly 4 white points as black in the training data. Figure A shows that the black point (7.2,1.4) is an outlier. Submit Figure B's classiÕer is better than Figure A's classiÕer, because Figure B's classiÕer classiÕes more of the training data correctly. Figure B's classiÕer is more likely to be over-Õt than Figure A's classiÕer. Figure B's classiÕer incorrectly classiÕes exactly 5 white points in the training data. Figure B shows that the black point (7.2,1.4) is colored incorrectly; it should actually be white. Submit3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 8/26 3c. Select all of the following statements that are true.  You have used 1 of 1 attempt Question 3d 0.99/3.0 points (graded) In the soft classiÕcation SVM model where we select coeÞcients ... to minimize 3d. Select each of the following cases when we would want to increase the value of .  A new point at (1,1) would be classiÕed as white by Figure A's classiÕer. A new point at (1,1) would be classiÕed as white by Figure B's classiÕer. A new point at (1,1) would be classiÕed as white by a -nearest-neighbor algorithm for . k 1 ≤ k ≤ 10 In Figure A, if the training data had 1000 more white points to the right of the classiÕer, a 1000-nearest-neighbor algorithm would classify a new point at (1,1) as white. Submit a0 am ∑max{0, 1 − ( + ) } + C j−1 n m∑i=1 aixij a0 yj ∑ i=1 m a2 i C We want a smaller margin even if it induces more classiÕcation errors in the training set. We are willing to accept a smaller margin in order to reduce classiÕcation errors in the training set. Neither.3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b2… 9/26 You have used 1 of 1 attempt Question 3e 3.0/3.0 points (graded) 3e. In the hard classiÕcation SVM model, it might be desirable to put the classiÕer in a location that has equal margin on both sides... (select all correct answers):  You have used 1 of 1 attempt Information for Questions 4a, 4b, 4c Seven diàerent regression models have been Õtted, using diàerent sets of variables. The Õgure below shows the resulting adjusted R-squared value for various models, as measured by cross-validation. Submit ...even though moving the classiÕer will usually result in fewer classiÕcation errors in the validation data. ...even though moving the classiÕer will usually result in fewer classiÕcation errors in the test data. ...when the costs of misclassifying the two types of points are very similar. Submit3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b… 10/26 Question 4a 3.0/3.0 points (graded) Which of the models would you expect to perform worst on a test data set? Model 6, because it has a slightly lower Adjusted than Model 5 and uses one more predictor. R2 Model 2, because it's the simplest of those with a high Adjusted R2 . Model 5, because it has the highest Adjusted R2 .3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b… 11/26  You have used 1 of 1 attempt Question 4b 3.0/3.0 points (graded) Under which of the following conditions would Model 3 be the most appropriate to use (select all correct answers)?  You have used 1 of 1 attempt Additional Information for Question 4c The table below shows the Akaike Information Criterion (AIC), Corrected AIC, and Bayesian Information Criterion (BIC) for each of the models. Model AIC Corrected AIC BIC 1 -5.58 -5.32 2.07 2 -5.67 -5.15 3.89 Model 1, because it has much lower Adjusted R2 . Submit Data collection for x6 is too expensive for it to be used in the model. Government regulations require using x2 for this sort of model. It is important to Õnd the simplest good model that includes x3 . The value of x3 is not known in time for use in the model. Submit3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b… 12/26 3 -6.51 -5.62 4.96 4 -4.77 -3.41 8.61 5 -2.80 -0.85 12.49 6 -1.31 1.35 15.90 7 0.19 3.71 19.31 Question 4c 2.25/3.0 points (graded) Based on the table above and the Õgure shown for Question 4a, select all of the following statements that are correct.  You have used 1 of 1 attempt Information for all parts of Question 5 Atlanta’s main library has collected the following day-by-day data over the past six years (more than 2000 data points): Adjusted (see Õgure above 4a) and BIC (see table above 4c) disagree about whether Model 1 is better than Model 2. R2 BIC suggests that Model 3 is very likely to be better than Model 7. Among Models 4 and 6, AIC suggests that Model 4 is as likely as Model 6 to be better. e(−4.77−(−1.31))/2 = 17.7% Among Models 4 and 6, AIC suggests that Model 6 is as likely as Model 4 to be better. e(−4.77−(−1.31))/2 = 17.7% Submit3/3/2020 GT Students and Verified | Midterm Quiz 1 | ISYE6501x Courseware | edX https://courses.edx.org/courses/course-v1:GTx+ISYE6501x+1T2020/courseware/a8e7783f3b6d4b21bbf5720bb6f02a92/5b27328248f3436fac8492b… 13/26 x = Number of books borrowed from the library on that day x = Day of the week x = Temperature x = Amount of rainfall x = Whether the library was closed that day x = Whether public schools were open that day Question 5a 2.0/2.0 points (graded) Select all data that are binary:  You have used 1 of 1 attempt Questions 5b and 5c 2.0/4.0 points (graded) The library believes that when there were more online searches of the library catalog yesterday, more books will be borrowed today (and fewer searches yesterday means fewer books borrowed today), so they add a new predictor: 1 2 3 4 5 6 [Show More]

Last updated: 3 years ago

Preview 1 out of 26 pages