There are 2 repositories under boston-housing-price-prediction topic.
Machine Learning - End to End Data Science Projects
This repository contains files for Udacity's Machine Learning Nanodegree Project: Boston House Price Prediction
Keras 101: A simple Neural Network for House Pricing regression
2018 [Julia v1.0] machine learning (linear regression & kernel-ridge regression) examples on the Boston housing dataset
All the essential resources and template code needed to understand major data science and machine learning libraries like Numpy, Pandas, Matplotlib and Scikit Learn with few small projects to demonstrate their practical application.
Implementation of 11 variants of Gradient Descent algorithm from scratch, applied to the Boston Housing Dataset.
Predicting Boston House Prices
Implement a perceptron from scratch
An Implementation of the Gradient Descent Algorithm on the 🏡Boston Housing DataSet🏡.
Boston Housing Prediction - 2nd project for Udacity's Machine Learning Nanodegree
Dataset Boston Housing Price prediction
These are all the assignments from Udacity Nanodegree Machine Learning course
Gradient Descent for N features using two datasets: Boston House data, Power Plant Data
Linear Regression , Cross Validation, k-mean clustering , Watershed , Gradients and Edge Detection , threshold , Correlation , Neural Network, Conventional Neural Network , Pneumonia Classification, Social Distancing, Rainfall Prediction, Boston Housing Price Prediction.
In this repository, a regression analysis is conducted using different machine learning and deep learning models. The study is led in order to choose the most suitable model by looking at different characteristics (models tuning, features scaling, etc).
The objective is to build a regression model to predict the price of houses.
Content for Udacity's Machine Learning curriculum
Machine Learning Nano-degree Project : To assist a real estate agent and his/her client with finding the best selling price for their home
This project is about predicting house price of Boston city using supervised machine learning algorithms. In this we used three models Multiple Linear Regression, Decision Tree and Random Forest and finally choose the best one. Furthermore, we briefly introduced Regression, the data set, analyzed and visualized the dataset.
The repository contains various Machine Learning based solutions for data analysis, regression and clustering problems
A project built as part of the udacity machine learning ND
Linear Regression model trained on Boston Housing Dataset
Data: Boston Housing Dataset (HousingData.csv) Programming language(s): R Tool(s): RStudio Business problem: To understand the drivers behind the value of houses in Boston and provide data-driven recommendation to the client on how they can increase the value of housing.The Boston housing dataset consisted of 506 observations and 14 variables. Project challenge(s): MEDV (Median value of homes in Boston) was identified as the dependent variable. While the rest, were the independent variables. The goal was to find out which among the independent variables were statistically significant in driving the house prices (MEDV). The dataset consisted of missing values and outliers. Some of the variables had a skewed distribution. There was multicollinearity among few independent variables. Our Approach: Prior to model building, we tidied up our dataset by eliminating the rows that contained missing values. Replacing the missing values with median and mean of those variables were also done. Considering the three approaches, median imputation(replacing missing values with mean) was found to be the best approach. As the dependent variable "MEDV" (median value of houses) was continuous(numerical) in nature, we implemented the Multiple linear regression to build our model. Additional models were built from Decision trees and Random forest. On further investigation, we discovered that the dependent variable had a skewed distribution. By log transformation of this variable, we were able to get a normal distribution. Post transformation, we found out that the model built from Multiple linear regression with log transformed MEDV was the best in terms of MSE (Mean squared error) value and Adjusted R^2. All the assumptions of linear regression were met.
Project #4 from the Cloud DevOps Engineer Nanodegree Program - Udacity
Regression by diviging data into bins and fitting different degree of polynomials on each bin.
In this project, XGBoost is applied to forecast real estate prices using the Boston Housing Dataset. The primary aim is to create an effective predictive model, assess its accuracy through metrics like Mean Absolute Error (MAE), and refine its performance by tuning hyperparameters with HYPEROPT.
Boston Housing Dataset Example
Evaluating the performance and predictive power of a model. Cross questioned several concepts of ML for better understanding.
Regression-PrediksiHargaRumahBoston-kaggle-ensamblemodel-supervisedlearning
The main motive of this project is Price Prediction on the Boston Housing dataset. and here mainly focused on the Implementation using Linear Regression Model.
The Linear regression model is implemented on Boston house prices dataset.
This project to predict Boston housing price using linear regression