Taxi demand forecasting: A HEDGE based tessellation strategy for improved accuracy

TL;DR

This paper compares two spatial tessellation strategies for taxi demand forecasting and introduces a hybrid HEDGE-based approach that adaptively selects the best strategy, resulting in improved accuracy across different city datasets and time scales.

Contribution

The paper proposes a novel hybrid tessellation algorithm using a non-stationary HEDGE approach for adaptive spatial partitioning in taxi demand forecasting.

Findings

Hybrid tessellation outperforms individual strategies consistently.

Achieved over 80% accuracy per km^2 at 60-minute intervals.

Performance varies with city geography and time of day.

Abstract

A key problem in location-based modeling and forecasting lies in identifying suitable spatial and temporal resolutions. In particular, judicious spatial partitioning can play a significant role in enhancing the performance of location-based forecasting models. In this work, we investigate two widely used tessellation strategies for partitioning city space, in the context of real-time taxi demand forecasting. Our study compares (i) Geohash tessellation, and (ii) Voronoi tessellation, using two distinct taxi demand datasets, over multiple time scales. For the purpose of comparison, we employ classical time-series tools to model the spatio-temporal demand. Our study finds that the performance of each tessellation strategy is highly dependent on the city geography, spatial distribution of the data, and the time of the day, and that neither strategy is found to perform optimally across the forecast horizon. We propose a hybrid tessellation algorithm that picks the best tessellation strategy at each instant, based on their performance in the recent past. Our hybrid algorithm is a non-stationary variant of the well-known HEDGE algorithm for choosing the best advice from multiple experts. We show that the hybrid tessellation strategy performs consistently better than either of the two strategies across the data sets considered, at multiple time scales, and with different performance metrics. We achieve an average accuracy of above 80% per km^2 for both data sets considered at 60 minute aggregation levels.