Data-Analysis-and-Regression-Modeling-Boston-Housing-and-Loan-Approval

Overview: This project focuses on conducting regression analyses on two distinct datasets—Boston Housing and Loan. The primary techniques employed are Linear Regression for the Boston Housing dataset and Logistic Regression for the Loan dataset.

Linear Regression (Boston Housing Dataset): Objective: Apply linear regression to predict the target variable "MV" in the Boston Housing dataset. The project aims to refine the dataset by reducing the number of columns using statistical measures such as p-value, correlation coefficient, and multiple R-squared statistics.

Implementation:

1. Use Python and relevant libraries for linear regression analysis.
2. Optimize the dataset by eliminating irrelevant features based on statistical significance.
3. Optionally, explore the possibility of replicating the analysis in Excel using the prepared dataset.

Logistic Regression (Loan Dataset): Objective: Implement logistic regression on the Loan dataset, focusing on predicting the target variable "Decision." This involves one-hot encoding for categorical variables and discarding irrelevant features.

Implementation:

1. Apply logistic regression in Python using appropriate libraries.
2. Perform one-hot encoding for categorical variables and eliminate irrelevant features.
3. Dataset Files:

The required datasets for both regression analyses are available in the "Files" section.