Reference no: EM133687089 , Length: 20 pages

Predictive Analytics

Assignment: Building and Evaluating Predictive Models using SAS Enterprise Miner

Objective:

• Demonstrate knowledge of building different types of predictive models using SAS Enterprise Miner
• Demonstrate skill and knowledge in applying predictive models in a real-life predictive analytics task
• Relate theoretical knowledge of predictive models and best practices to application scenarios

Business Case - Predictive Model for Vehicle Price Prediction

Alpha (Pvt) Ltd is an USA online car sales platform for providing an effective car buying and selling service. In order to help boost sales transactions, the management of Alpha is in the process of building a car price estimation system to help second-hand car sellers to sell their cars at the best price.

Alpha management is very keen to trial predictive modeling for this task and has gathered a historic car sales dataset from a publicly available data repository. The dataset contains 21 variables describing previously sold cars. The attributes include the selling price of cars, year, odometer reading, fuel type, condition, location, etc. The list of attributes and their descriptions are given below.

The management of Alpha (Pvt) Ltd. is considering you as an external consulting group to outsource the task to develop a reliable predictive model to predict the selling price of the cars, using the aforementioned historical dataset. Alpha has provided you with sample data sets of BMW, Mercedes, Toyota and Honda cars to build separate price-prediction models. They also wish to compare and contrast the pricing models between two car brands.

You have to only select one dataset from the four datasets (in the Training data folder). Based on the selected vehicle dataset, you are required to build different predictive models, compare and contrast which is the best model for the selected dataset. You are also provided with a scoring dataset (in the Scoring data folder) which you need to use for price prediction.

Setting up the project and exploratory analysis
Needs to provide a screenshot as evidence for each sub-section of this question.
Create a new project and create a data source based on the selected dataset. Make sure the Role and Level assigned to each variable is correct.
Carry out data exploration by using a StatExplore Node. Explain your findings with regard to your vehicle dataset.
Create a Data Partition with 70% of the data for training and 30% for validation.

Decision tree-based modeling and analysis
Carry out the following modeling tasks for the selected vehicle dataset.
Create two Decision Tree models. Use two-way and three-way splits to create the two separate decision tree models. Provide the relevant diagrams of the Decision trees.
For each decision tree,
How many leaves are in the optimal tree?
Which variable is used for the first split?
What are the competing splits for this first split?
Which of the decision tree models appears to be better? Justify your answer.
Refer to the selected decision tree model in part (b) and
Identify leaf nodes which have good predictive performance (two leaf nodes) and poor predictive performance (two leaf nodes).
Provide justifications for your selections.

Write down the rules for the pathways leading up to each selected leaf node.
Regression-based modeling and analysis
In preparation for regression, is any imputation of missing values needed? If yes, should you do this imputation before generating the decision tree models? Why or why not?
Use an Impute node connected to Data Partition node to handle missing values. Which variables have been imputed?
Are there any ordinal variables? Use the replacement node to assign relevant values.
Conduct data exploration to select the best variables for the model with Variable Clustering node. Describe and justify how you ascertained the best variables to the model.
Create a Regression model using the set of variables you identified as suitable in part d. You can choose the stepwise selection and use validation error as the selection criterion.
Run the Regression node and view the results.
Which variables are included in the final model? Explain what this means to the vehicle sales organization (very briefly).
What is the validation Average Square Error (ASE) (or Mean Square error (MSE))? What does this mean in a predictive model?

Model Comparison and Scoring
Use the model comparison to compare and contrast the results from the decision trees and regression-based analysis. Provide a summary table for comparison. Describe and justify how you ascertained the better model.
Would it have been sufficient to use only one modeling technique (decision tree or regression)? Provide justifications for your answer. Use the outcome of 4a solutions.
Use the scoring data sets to score using the best predictive model for your vehicle brand. Explain the output using plots.

Comparison between Car Brands
Choose another car brand and apply the SAS model flow to carry out an analysis between two car brands.
What are the factors that are significant in determining the price of the two car brands? Are those factors the same or different across the two brands? Justify with external knowledge. (e.g., What do the differences in features/variables say about the buyer's interest in different models?)

Compare the best selected predictive models for the two car brands. Do you recommend decision trees or regression? Outline reasons.
What are your suggestions to improve the car price prediction models of Alpha Management?