Part B - Predictive Analytics Assignment 2- Part A PDF

Preview

Summary

Predictive Analytics Assignment 2- Part A...

Description

a. Which variables were used in the predictive models to determine the price of the four brands? Discuss further comparing the feature importance of four brands (eg: What do the differences in features/variables say about the buyers interest in different models?). For BMW, The variables used to determine the price of the models are year, long, odometer, cylinders, paint_color, transmission, type, condition, drive and fuel. Initially, the buyers interested to know about the manufacturing year of the model. If the model of BMW is latest model then the buyer is more interested to buy this car (i.e. the r-square of year is 0.180920 which is higher than other variables). While the buyer is also interested in other variables such as long, odometer, cylinders, paint_color, transmission, type, condition, drive and fuel but he is less interested in these features of the brand. Hence, it creates less impact on the price of the brand and the buyers interest as well.

b. Compare the best selected predictive models for the four brands. Do you recommend decision trees or regression? Outline reasons. For BMW,

Among these three models, Decision tree (2) i.e three split model is the better model because the average square error is smaller than the other two models.

It is not sufficient to use only one modeling technique (decision tree or regression) because it varies upon the nature of the dataset. Although, decision tree model is the best model for predictive analysis in comparison to regression model because it is difficult to analyse the output of the model but logistic regression is suitable for maintaining the better account of the relationship whereas decision tree is limited for sequential relationship only.

c. As a team of data analysts, what are your suggestions to improve the car price prediction models of Beta Management? ...