Midterm Report Review from jx255

[ANGELA6XU]

In general, the structure of this report is straightforward and concrete. It shows a clear process from data cleaning, feature selections, model selections and future development. The histograms and descriptive statistics can help illustrate and determine the feature selection well.

For cleaning the original data set, I have noticed that around 10k listings have been deleted. So, what concerns to me is that will this deletion method for dealing with missing/outliers cause information loss? It would be great if you would try other methods for handling the missing data, such as Mean/Mode completer or k-means clustering.

Besides the ridge regression, it would be great if you could try different other models and describe the reasons for model selection and interpretations in more details.