Privacy-Preserving Taxi-Demand Prediction Using Federated Learning

TL;DR

This paper introduces a federated learning approach for taxi-demand prediction that preserves data privacy while maintaining high accuracy, enabling multiple providers to collaboratively improve transportation models without sharing sensitive data.

Contribution

It presents a novel federated learning framework for taxi-demand prediction that ensures privacy and achieves accuracy comparable to centralized models.

Findings

Predicts demand with less than 1% error compared to centralized models.

Enables collaboration among taxi providers without sharing sensitive data.

Demonstrates effectiveness on real-world data from 16 providers in Japan.

Abstract

Taxi-demand prediction is an important application of machine learning that enables taxi-providing facilities to optimize their operations and city planners to improve transportation infrastructure and services. However, the use of sensitive data in these systems raises concerns about privacy and security. In this paper, we propose the use of federated learning for taxi-demand prediction that allows multiple parties to train a machine learning model on their own data while keeping the data private and secure. This can enable organizations to build models on data they otherwise would not be able to access. Evaluation with real-world data collected from 16 taxi service providers in Japan over a period of six months showed that the proposed system can predict the demand level accurately within 1\% error compared to a single model trained with integrated data.