What is the best way to decide how many epochs of training to perform? It is always obvious looking at the decision boundary when the model begins to overfit. None of the others. As soon as the value of the Testing dataset performance begins to decrease. As soon as the value of the Tuning dataset performance begins to decrease. As soon as the value of the Training dataset performance (accuracy, F1.) begins to decrease. As soon as the value of the Testing dataset loss begins to increase. As soon as the value of the Tuning dataset loss begins to increase. As soon as the value of the Training dataset loss begins to increase.

You decide to run a simpler model to predict churn, using only the variables tenure (in months) and TotalCharges (in US$). The output is given below. The AIC of this model is 4727.6 (in contrast to the AIC of 4240 for the full model). On the basis of this which model would be expected to give superior predictive performance? Actual ## Coefficients: ## Estimate Std. Error z value Pr(>|z|) ## (Intercept) 2.471e-01 5.360e-02 4.611 4.01e-06 *** ## tenure < 2e-16 *** -1.124e-01 5.816e-03 -19.334 ## TotalCharges 8.236e-04 5.618e-05 14.660 < 2e-16 *** ## No --- ## Signif. codes: 0 ## Yes Yes ## Null deviance: 5701.5 on 4921 ## Residual deviance: 4721.6 on 4919 ## AIC: 4727.6 515 345 ## (Dispersion parameter for binomial family taken to be 1) ## Predicted ***** No 795 3267 0.001 Confusion Matrix (Training) **** Actual 0.01 Yes No degrees of freedom degrees of freedom Yes The simpler model (with just tenure and TotalCharges) The full model (with all variables) 0.05 0.1 220 145 Predicted No 339…

Medical records show a sample population of 1000 people, of those 1000 people, 98% do not have a terminal illness and 2% do have a terminal illness. A Health Insurance company would like try out a new cheaper test for terminal illness. Their results show that 98% of the people that do have a terminal illness test positive, while 1% of the people who do not have a terminal illness test positive for one.  A corporation known as Ken’s Kids is concerned about patients that are slipping through the cracks with this new medical testing. If the new medical testing is adopted, what % of the people will be misdiagnosed as not having a terminal illness, but really have one? Assuming a population of 200 million people, how many people that have a terminal illness, given this new testing will never know that they do? (Please show all work , and have a legend for symbols).