James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio. James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Siva and the data scientist on his team work together to develop the following decision tree Click the soon to view the decision tree) The data science team tested the full decision model on a validation set resulting in 518 correct classifications Chok the icon to view the validation set using the full decision troo) Read the requirements Requirement 1. Prune the tree at topth 3. Using the pruned troo, classily each loan in the validation sample as repay or default (if the probability of detauit is greater than 05 classify the loan as default) Calculate the proportion of loans correctly classified Start by classifying each loan in the validation sample as (0) Repay or (1) Delaviy using the pruned tree Model Prediction Observation Income Credit Score Actual Outcome (Pruned Tree) (2) (3) (4) (5) 1 $ 85,000 710 (0) Repay 2 $ 62,000 650 (1) Default 3 $ 72.000 660 (0) Ropay 75,000 640 (0) Repay 5 71,000 680 (0) Repay 6 5 59,000 705 (0) Repay 10 4 $ 5 7 James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio. James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the poor-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree: (Click the icon to view the decision tree) The data science team tested the full decision model on a validation set resulting in 5/8 correct classifications Click the icon to view the validation set using the full decision troo) Read the requirements Figure FU U ULICI than 0.5 classify the loan as de Start by classifying each loan in Depth 1 Ce 675 CUTI Observation Income Credit Score (2) $ 85,000 Depth 2 $70,000 $60,000 CUT2 CUT 2 62,000 7 Income 72.000 4 $ Dw 75,000 5 $ 71.000 $ 59.000 7 $ 48.000 Depth 3 $55,000 I Crr) 2 Income 1 2 $ 3 S $ Income pay Etext pages Calcula Repuy Default Check answer untir James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree Click the icon to view the decision tree) The data science team bested the full decision model on a validation set resulting in 5/8 correct classifications Click the icon to view the validation set using the Nal decision troo) Read the requirements Data table - X neyun. than 05 classify the loan as Model Prediction Start by classifying each loan Observation Income Credit Score Actual Outcome (Full Tree) (1) (2) (3) Observation (4) (5) Income 1 $ 85,000 710 (1) (0) Repay (0) Repay (2) 2 $ 62.000 1 $ (1) Default (1) Default 85.000 3 $ 72.000 660 2 (0) Repay (0) Ropay $ 62.000 $ 75,000 640 (0) Repay $ 72.000 (0) Ropay 5 $ 71.000 680 (0) Repay (0) Ropay $ 75.000 $ 59,000 705 5 $ (0) Ropay (1) Default 71,000 5 6 48.000 (1) Default $ 59.000 (0) Repay 8 $ 57.000 685 7 $ 48,000 (0) Repay (1) Default 650 4 3 4 690 M Etext pages Calce Print Done Check answer James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio, James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree Click the icon to view the decision treo) The data science team tested the full decision model on a validation set resulting in 5/8 correct classifications, Click the icon to view the validation set using the full decision tree) Read the requirements X Requirements I.VN my sy than 0.5 dassity the loan as det 1. Prune the tree at depth 3. Using the pruned troo, classily cach loan in the Start by classifying each loan in Validation sample as repay or default (if the probability of default is greater than 05 classify the loan as default) Calculate the proportion of loans Observation Income correctly classified 2. Based on your answer to requirement and the results from validation using (1) (2) the full troo, which decision tree should James use to identity default and 1 s 85,000 repay loans? 3. James has to present both models and the conclusions to the president of 2 $ 62,000 Keebler-Olson He knows that in the past the president has preferrey using 3 72.000 models based on full decision trees because they seem to fit the training data more closely How should James explain the pruned decision tree model? 75.000 $ 71.000 50,000 7 $ 48,000 Print Done $ 4 $ 5 5 $ James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio. James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Siva and the data scientist on his team work together to develop the following decision tree Click the soon to view the decision tree) The data science team tested the full decision model on a validation set resulting in 518 correct classifications Chok the icon to view the validation set using the full decision troo) Read the requirements Requirement 1. Prune the tree at topth 3. Using the pruned troo, classily each loan in the validation sample as repay or default (if the probability of detauit is greater than 05 classify the loan as default) Calculate the proportion of loans correctly classified Start by classifying each loan in the validation sample as (0) Repay or (1) Delaviy using the pruned tree Model Prediction Observation Income Credit Score Actual Outcome (Pruned Tree) (2) (3) (4) (5) 1 $ 85,000 710 (0) Repay 2 $ 62,000 650 (1) Default 3 $ 72.000 660 (0) Ropay 75,000 640 (0) Repay 5 71,000 680 (0) Repay 6 5 59,000 705 (0) Repay 10 4 $ 5 7 James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio. James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the poor-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree: (Click the icon to view the decision tree) The data science team tested the full decision model on a validation set resulting in 5/8 correct classifications Click the icon to view the validation set using the full decision troo) Read the requirements Figure FU U ULICI than 0.5 classify the loan as de Start by classifying each loan in Depth 1 Ce 675 CUTI Observation Income Credit Score (2) $ 85,000 Depth 2 $70,000 $60,000 CUT2 CUT 2 62,000 7 Income 72.000 4 $ Dw 75,000 5 $ 71.000 $ 59.000 7 $ 48.000 Depth 3 $55,000 I Crr) 2 Income 1 2 $ 3 S $ Income pay Etext pages Calcula Repuy Default Check answer untir James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree Click the icon to view the decision tree) The data science team bested the full decision model on a validation set resulting in 5/8 correct classifications Click the icon to view the validation set using the Nal decision troo) Read the requirements Data table - X neyun. than 05 classify the loan as Model Prediction Start by classifying each loan Observation Income Credit Score Actual Outcome (Full Tree) (1) (2) (3) Observation (4) (5) Income 1 $ 85,000 710 (1) (0) Repay (0) Repay (2) 2 $ 62.000 1 $ (1) Default (1) Default 85.000 3 $ 72.000 660 2 (0) Repay (0) Ropay $ 62.000 $ 75,000 640 (0) Repay $ 72.000 (0) Ropay 5 $ 71.000 680 (0) Repay (0) Ropay $ 75.000 $ 59,000 705 5 $ (0) Ropay (1) Default 71,000 5 6 48.000 (1) Default $ 59.000 (0) Repay 8 $ 57.000 685 7 $ 48,000 (0) Repay (1) Default 650 4 3 4 690 M Etext pages Calce Print Done Check answer James Silva is a management accountant at Keebler-Olson, where he is in charge of their investment portfolio, James worked with a data scientist to develop a model that predicts how a given loan will perform in the future based on the characteristics of the borrower available on the peer-to-peer lending platform Mandel Credit. James Silva and the data scientist on his team work together to develop the following decision tree Click the icon to view the decision treo) The data science team tested the full decision model on a validation set resulting in 5/8 correct classifications, Click the icon to view the validation set using the full decision tree) Read the requirements X Requirements I.VN my sy than 0.5 dassity the loan as det 1. Prune the tree at depth 3. Using the pruned troo, classily cach loan in the Start by classifying each loan in Validation sample as repay or default (if the probability of default is greater than 05 classify the loan as default) Calculate the proportion of loans Observation Income correctly classified 2. Based on your answer to requirement and the results from validation using (1) (2) the full troo, which decision tree should James use to identity default and 1 s 85,000 repay loans? 3. James has to present both models and the conclusions to the president of 2 $ 62,000 Keebler-Olson He knows that in the past the president has preferrey using 3 72.000 models based on full decision trees because they seem to fit the training data more closely How should James explain the pruned decision tree model? 75.000 $ 71.000 50,000 7 $ 48,000 Print Done $ 4 $ 5 5 $
