Table of Contents

1. About The Project
2. Motivation
3. Installation
4. Step By Step Approach
5. File Discription
6. Results
7. Resources
8. Acknowledgements

About The Project

The main goal of this project is to predict the accommodation prices from Airbnb data and to determine the features responsible for the price.

Motivation:

In this project, I was interested in predicting accommodation prices with some intuitive analysis and modelling techniqies with help of Airbnb Seatle dataset from Kaggel.

1. Finding all the key features which determine the price
2. How to choose the right place for good price?
3. What feature are directly correlated in the dataset?
4. What are top features in predicting the price ?
5. Which model would be useful to predict the price with some good accuracy?

Installation

Required libraries:

1. Pandas
2. Numpy
3. Sckit Learn
4. Linear Regression
5. XGBoost

Step By Step Approach

1. Lets first explore the dataset first - Shape, type of columns and etc.
2. Data preprocessing - Remove or imputing missing values & How we deal with them?
3. Explore Insigts to get key aspects of the data and its key features.
4. Feature Engineering - There are lot techniques to determine the right feature to predict the prices.
5. Modelling

File Discription

There is notebook name called Airbnb_Price_Prediction.ipynb which is used for the complete analysis.

Results

The results from code is explained in this blog here

Resources:

1. https://www.kaggle.com/airbnb/seattle
2. Airbnb website

Acknowledgements

Credit for kaggle for the datasets and the description of the datasets link available here