John also knows that decision tree is another classification method and would like to seek your advice on whether decision tree or Naive Bayes is more appropriate for this. Explain your answer. 2. Bank A would like to build a logistic regression model to predict whether a new customer will accept a loan offer. The model is built based on the following predictor attributes Table 2.1 The following is obtained after training has performed on a training set of Bank A customers. ln(1P(loan=yesP(loan=yes))=10.620.05467x1+0.0521x2+0.117x3+0.001x40.673x6+3.132x70.611x8 (a) [4 pts] Based on this result, briefly explain the impact of each attribute on the probability of loan acceptance. (b) [4 pts] What is odd that a customer use Internet banking facilities will accept a lo offer compared to one who does not? c) [7 pts] The following is the model's validation confusion matrix. Table 2.2 John also knows that decision tree is another classification method and would like to seek your advice on whether decision tree or Naive Bayes is more appropriate for this. Explain your answer. 2. Bank A would like to build a logistic regression model to predict whether a new customer will accept a loan offer. The model is built based on the following predictor attributes Table 2.1 The following is obtained after training has performed on a training set of Bank A customers. ln(1P(loan=yesP(loan=yes))=10.620.05467x1+0.0521x2+0.117x3+0.001x40.673x6+3.132x70.611x8 (a) [4 pts] Based on this result, briefly explain the impact of each attribute on the probability of loan acceptance. (b) [4 pts] What is odd that a customer use Internet banking facilities will accept a lo offer compared to one who does not? c) [7 pts] The following is the model's validation confusion matrix. Table 2.2