Predictive Price Modelling for Airbnb listings

The project aims at predicting the price of an Airbnb listing given a number of features. The project involved exploratory data analysis, data pre-processing, feature selection, Model Fitting, Model Comparison and deploying the containerised Web-app on AWS using CI/CD Pipeline.

Project Resources

What is the goal of the project ?

Project Overview

Project Overview

End Result

About Dataset

Exploratory Analysis

Number of listings: Country and city wise
Number of listings by Room Type
Listing Price by city and country
Listing Price by Room type

Feature Engineering: What features will be useful in predicting the listing price ?

Distribution of various features against listing price

Data pre-processing and cleaning

Data Pipeline
Data pre-processing operations
Preprocessing pipeline using Scikit-Learn
Data Splitting

Modelling: Training Machine learning models, Model Selection

Linear Regression

Feature Importance Score based on Linear Regression
Model Scalability, learning curve, model performance using Scikit-Learn’s learning_curve
Linear Regression: Model Scalability, learning curve, model performance

Decision Tree Regressor

Feature importance score: Decision Tree
Hyper-parameter tuning using Grid Search and Randomised Search Cross Validation
Grid Search Parameters for tuning hyper-parameters
Decision Tree: Hyper-parameter tuning
Decision Tree: Model Scalability, learning curve, model performance

Model Evaluation and Comparison

Model Comparison on Test Data

Deployment, Serving and Production: CI/CD Pipeline

Model Predictions using REST API

Model in Production: FLASK, Docker, AWS CI/CD Pipeline

Model in Production: FLASK, Docker, AWS CI/CD Pipeline

Project Resources

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store