Monitoring and Predicting Subway Passenger Demand in São Paulo City Using Machine Learning

Local Chapter São Paulo, Brazil Chapter

Coordinated byBrazil ,

Status: Completed

Project Duration: 31 May 2023 - 08 Jul 2023

Open Source resources available from this project

Project background.

São Paulo city is the capital of the Brazilian state with the same name. It is the most populous city in Brazil and the fourth most populous in the world. São Paulo Metropole or the Great São Paulo Area joins 39 cities with around 27 million people and has different urban problems, including public transportation planning.

The problem.

The São Paulo city subway system comprises 6 lines with 91 stations. Every day on average more than 4 million people are transported. Although the system is under continuous update with new lines and stations being constructed, the passenger demand is still higher than transportation capacity in critical times every day. Only recently in the last years, the data for passenger demand has been opened to public access. There is no open monitoring system, dashboards, or predictive models to help the people and community decision-makers to understand the evolution and forecast the passenger demand for better urban planning.

Project goals.

In this project, the Omdena São Paulo, Brazil Chapter team aims to develop a monitoring and predicting system for subway passenger demand using machine learning.With a duration of 5-weeks, this project aims to: - Data Collection and Preprocessing. - Exploratory Data Analysis - Data Visualization. - Model Development and Training. - Web App Development.

Project plan.

  • Week 1

    Problem statement. Data collection, cleaning, and preprocessing. Creation of a common data source for the project.

  • Week 3

    Development and training of forecast and machine learning models.

  • Week 4

    Development of web application with dashboards and models created.

  • Week 5

    Web app deployment. Project final discusions and next steps.

Learning outcomes.

Data collection, data cleaning and preprocessing, exploratory data analysis, dashboard creation and insights, development and model training, and web app development.

Share project on: