question archive You have used a dataset to train the data with the following attributes Due to various data restrictions, the data you are provided includes only the following variables: · Target variable · price: Apartment price (thousands of $) · Attributes · distance – Distance from the sea (ft) · size – House size (sqr ft) · shops – Number of cafés and convenient stores in a 1-mile radius of the apartment · mall – Whether a shopping mall in a 3-mile radius of the apartment The real estate company impressed with your work so far and gets you access to the full data set which includes many additional attributes on each apartment
Subject:BusinessPrice: Bought3
You have used a dataset to train the data with the following attributes
Due to various data restrictions, the data you are provided includes only the following variables:
· Target variable
· price: Apartment price (thousands of $)
· Attributes
· distance – Distance from the sea (ft)
· size – House size (sqr ft)
· shops – Number of cafés and convenient stores in a 1-mile radius of the apartment
· mall – Whether a shopping mall in a 3-mile radius of the apartment
The real estate company impressed with your work so far and gets you access to the full data set which includes many additional attributes on each apartment.
Based on the evaluation metrics for regression analysis such as domain knowledge validation, holdout validation, how would you create a fitting graph and a learning curve using the complete dataset to improve your model creation process?
Fitting graph = A fitting graph shows the generalization performance as well as the performance on the training data. but plotted against model complexity.
Learning curve = A learning curve shows the generalization performance plotted against the amount of training data used. Compares two properties, the accuracy and training instances.
Note that I am not asking you to create an actual graph, but instead to describe in words what the axes would be and how the graph could help you select a model to use on the complete dataset.