sanketmaneds / decision_tree

This repository contains introductory notebooks for Decision tree

Decision_Tree

Use decision trees to prepare a model on fraud data treating those who have taxable_income <= 30000 as "Risky" and others are "Good"

Data Description :

Undergrad : person is under graduated or not

Marital.Status : marital status of a person

Taxable.Income : Taxable income is the amount of how much tax an individual owes to the government

Work Experience : Work experience of an individual person

Urban : Whether that person belongs to urban area or not

Decision Tree

Assignment

About the data:

Let’s consider a Company dataset with around 10 variables and 400 records.

The attributes are as follows:

 Sales -- Unit sales (in thousands) at each location

 Competitor Price -- Price charged by competitor at each location

 Income -- Community income level (in thousands of dollars)

 Advertising -- Local advertising budget for company at each location (in thousands of dollars)

 Population -- Population size in region (in thousands)

 Price -- Price company charges for car seats at each site

 Shelf Location at stores -- A factor with levels Bad, Good and Medium indicating the quality of the shelving location for the car seats at each site

 Age -- Average age of the local population

 Education -- Education level at each location

 Urban -- A factor with levels No and Yes to indicate whether the store is in an urban or rural location

 US -- A factor with levels No and Yes to indicate whether the store is in the US or not

The company dataset looks like this:

Problem Statement: A cloth manufacturing company is interested to know about the segment or attributes causes high sale. Approach - A decision tree can be built with target variable Sale (we will first convert it in categorical variable) & all other variable will be independent in the analysis.