Compare and contrast results from TWO models designed to predict levels of potential sale price (fair value) of real estate assets in a specific area given predefined asset and environmental characteristics .

use “Python in Real Estate Valuations.pdf” as reference to complete the Fintech Use Case below. Compare and contrast results from TWO models designed to predict levels of potential sale price (fair value) of real estate assets in a specific area given predefined asset and environmental characteristics (modified data is provided). Specifically, your IoT FinTech team members are interested to see the effect of “number of rooms” variable on the mean asset value. You are free to choose any two relevant models Your task is to critically explain your steps and results and show model coefficients and model accuracy, for example in mean square error (MSE) and/or R^2. Model choices 1.Linear Regression 2.RANSAC Regressor 3.LASSO 4.Polynomials 5.Decision Tree 6.Random Forest Your team members are keen to learn about python and would like to see and read the python script with simple explanations of your steps. As a result, delivery is in one python.py script format as with ‘’’’’’ explanations of your steps. The aim is to describe your detailed steps from input variables to model parameters and compare and contrast final results in a critical, concise and logical way. Recommended formats: *(image file)* 1.Explain Steps a)Point out the purpose of finch use case? b)Import data, define the value of X and Y, define a basic graphical functional form, define model train and test variables of X and Y. c)Select two models: i.What are the models and why? ii.The pros and cons of two models iii.Etc. 2.Describe line of code a)Start code b)End code 3.Explain results a)Explain results of two models respectively i.Slope and intercept ii.MSE & R2 (the less the value of MSE, the better the results; the better the results as R2 close to 1) 1.Train MSE & R2 2.Test MSE & R2 b)Compare two models i.the less the value of MSE, the better the results ii.the better the results as R2 close to 1 iii.compare MSE & R2 of both models iv.However, neither of them is the best. There could results in the situation of underfitting in one of the models although one is better than another one. 4.Conclusion