Predicting Urban Rental & Airbnb Pricing in Kenya

Local Chapter Kitengela, Kenya Chapter

Coordinated byKenya ,

Joseph Mwaura Muthoni

Status: Completed

Project Duration: 13 Jun 2023 - 17 Aug 2023

Open Source resources available from this project

Github Repository

Project background.

The dynamics of urban rental markets have seen a significant evolution with the advent of online platforms like Airbnb, where hosts can list their properties for short-term rentals. Determining an optimal price that appeals to potential guests while maximizing host revenue can be a challenging endeavor given the multitude of variables at play, such as location, property attributes, seasonal demand, and local events.

The project in focus aims to tackle this very issue – determining the optimal rental price for Airbnb listings. Currently, hosts may rely on intuition or manual comparisons with other local listings to set their prices. This can lead to inaccuracies, underpricing, or overpricing, resulting in lower occupancy rates and sub-optimal income.

The problem.

The project in focus aims to tackle this very issue – determining the optimal rental price for Airbnb listings. Currently, hosts may rely on intuition or manual comparisons with other local listings to set their prices. This can lead to inaccuracies, underpricing, or overpricing, resulting in lower occupancy rates and sub-optimal income.

Project goals.

The goal of this project is to design and develop a predictive model using historical data and sophisticated algorithms. This model will accurately predict rental prices that are competitive within the market while promoting higher occupancy rates for hosts. By harnessing the power of data analytics and machine learning, the project seeks to empower Airbnb hosts with dynamic and data-driven pricing strategies, ultimately leading to an enhancement of their rental income.

Project plan.

  • Week 1

    – Data collection
    – Data scraping and sourcing

  • Week 2

    – Data preprocessing
    – Data cleaning

  • Week 3

    Data Exploration

  • Week 4

    Feature Selection

  • Week 5

    Model development and Training

  • Week 6

    Evaluating the Model

  • Week 7

    Model Integration

  • Week 8

    Model Deployment

Learning outcomes.

Participants will gain knowledge on the skills used machine learning skills and they will also gain people skills such as leadership and communications and others. They will also have a project to be proud of .They will network with other engineers across the globe.

Share project on: