https://github.com/andrew2077/airbnb-model

Airbnb-model
https://github.com/andrew2077/airbnb-model

Last synced: about 5 hours ago
JSON representation

Airbnb-model

• Host: GitHub
• URL: https://github.com/andrew2077/airbnb-model
• Owner: Andrew2077
• Created: 2022-08-16T21:02:33.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2023-02-11T17:59:35.000Z (almost 2 years ago)
• Last Synced: 2023-09-17T16:26:33.294Z (about 1 year ago)
• Language: Python
• Size: 5.11 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Airbnb New User Bookings

- Where will anew guest book their first travel experience?

- The Kaggle [Airbnb New User Bookings](https://www.kaggle.com/competitions/airbnb-recruiting-new-user-bookings/overview) dataset contains information about users who have signed up for Airbnb and is focused on predicting where a new user will book their first travel experience. more info in the link

- check out the decumentation with streamlit [here](https://andrew2077-airbnb-model--airbnb-cpucud.streamlit.app) 

___

## **Description**

With the use of travel destination predictions and personalized booking recommendations, this project aims to streamline the booking process for new users of the Airbnb site.

___

## **Requirements**

- [**Sklearn**](https://scikit-learn.org/stable/install.html) (scikit-learn (sklearn) is a popular Python library for machine learning that provides a wide range of tools)

- **numpy**/**pandas**

- **[streamlit](https://docs.streamlit.io/)** (Streamlit is a Python library that allows you to create interactive web-based applications for machine learning and data science.)

- **[matplotlib](https://matplotlib.org/stable/contents.html)** (Matplotlib is a plotting library for the Python programming language and its numerical mathematics extension NumPy.)

- **[plotly](https://plotly.com/python/)** (is a data visualization library that allows you to create interactive plots and graphs.)

- **[skforecast](https://joaquinamatrodrigo.github.io/skforecast/0.4.3/index.html)** ( is a *python* library that eases using scikit-learn regressors as multi-step forecasters.)

___

## **Table Of Contents**

- [Airbnb New User Bookings](#airbnb-new-user-bookings)

  - [**Description**](#description)

  - [**Requirements**](#requirements)

  - [**Table Of Contents**](#table-of-contents)

  - [**Pre-Processing**](#pre-processing)

  - [**Guideline**](#guideline)

  - [**Results**](#results)

  - [**Future Work**](#future-work)

  - [**Contributing**](#contributing)

___

## **Pre-Processing**

* Handling categorical data

* handling time series data

* handling missing data

* feature engineering

more about it [here](https://andrew2077-airbnb-model--airbnb-cpucud.streamlit.app)

___

## **Guideline**  

1. just visit our deployed model with the documentation [here](https://andrew2077-airbnb-model--airbnb-cpucud.streamlit.app)

1. otherwise if you wish to run it locally just run '✈️_Airbnb.py' with the instruction below in terminal

   >streamlit run ✈️_Airbnb.py

___

## **Results**

- used 3 Algorithm 

  - Decision Tree

  - Random Forest

  - XGBoost

- used differnt filling values techniques that altered model accuracy slightly 

- playalong with the model [here](https://andrew2077-airbnb-model--airbnb-cpucud.streamlit.app/Visualizor)

  - just Enable the model Aaccuracy checkbosx 

___

## **Future Work**

- [ ] add more models

- [ ] use more filling values techniques

- [ ] add more visualizations 

---

## **Contributing**

Any kind of enhancement or contribution is welcomed.

Suggestions are also welcomed.