11. Assignment 11: Model Comparison#

11.1. Quick Facts#

accept the assignment

Due: 2020-11-24 11:59pm

11.3. Assessment#

Table 11.1 compare models and make a recommendation#

task

skill

determine the best model for a given dataset

compare (2)

test the model on test data and interpret in context

classification, clustering, OR regression (2)

choose and justify appropriate parameters parameter grid for the context

classification, clustering, OR regression (2) AND process (2)

evaluate fit of the model while varying the cross validation parameters and interpret

evaluate (2)

interpret the classifier performance in the context of the dataset

process (2)

analyze the impact of model parameters on model performance

process (2)

usse EDA techniques to interpret the experimental results

summarize (2), visualize (2)

Choose a dataset, it can be appropriate for classification, regression, or clustering. Fit at least two models for the same task and choose the appropriate metrics to compare the fit. Decide which model you would recommend based on a realistic setting for that dataset and include evidence justifying that choice. Summarize your findings with plots and tables as appropriate.

This will be easiest if you use a dataset you’ve used on for one of the previous assignments or choose another.

Think Ahead

How would this decision making compare for a more complex model or in more realistic setting.