+61480015851
161.324/161.777: Predicting a Binary Target Variable - Data Mining IT Assessment Answer
Download Solution
Order New Solution
Subject Code: 161.324/161.777
Internal Code: 1AGJBG
Exploration and partitioning
1. Briefly explain why TargetAmt should not be used to predict TargetBuy.
2. What proportion of individuals in this dataset purchased a health product?
3. Visualize the dataset. Which input variables (or pair-wise combinations of input variables) do you expect will be useful for discriminating customers that purchase a product? Present a graphic that best supports your answer.
4. Partition the data randomly into training:validation: test sets using a 60:20:20 split respectively (using the default random seed of 12345). In one sentence each, explain the general purpose of each subset of the partition.
IT Assessment Answer
General information Completed assignments are to be submitted online via Stream in MS Word or PDF format. You are encouraged to include the relevant computer output from SAS Enterprise Miner (SAS EM), but this must be presented clearly and concisely and accompanied by your own interpretations. Please only submit computer output that directly supports your written conclusions. You will probably need to consult the study guide, lectures, and tutorials to complete this assignment. You are also encouraged to examine the help files of SAS EM, accessible by typing F1. They contain a large amount of useful information on all of the nodes in SAS EM. Part 1: Predicting a binary target variable A supermarket chain is offering a new line of organic products and wants to know which customers from their customer loyalty programme should be targeted for further advertising. As an initial trial of the products, the supermarket provided coupons for the products to their loyalty customers and collected data on whether they made a purchase. The dataset contains over 20,000 cases and has the following 10 columns:
Exploration and partitioning
1. Briefly explain why TargetAmt should not be used to predict TargetBuy.
2. What proportion of individuals in this dataset purchased a health product?
3. Visualize the dataset. Which input variables (or pair-wise combinations of input variables) do you expect will be useful for discriminating customers that purchase a product? Present a graphic that best supports your answer.
4. Partition the data randomly into training:validation: test sets using a 60:20:20 split respectively (using the default random seed of 12345). In one sentence each, explain the general purpose of each subset of the partition.
This IT Assessment has been solved by our IT experts at My Uni Paper. Our Assignment Writing Experts are efficient to provide a fresh solution to this question. We are serving more than 10000+ Students in Australia, UK & US by helping them to score HD in their academics. Our Experts are well trained to follow all marking rubrics & referencing style.