A Hidden Markov Model for Route and Destination Prediction

TL;DR

This paper introduces a simple, efficient Hidden Markov Model-based algorithm for predicting driver destinations and routes using recent trip data, without needing complex transition matrices, validated by high success rates.

Contribution

It presents a novel, low-complexity HMM algorithm that predicts driver routes and destinations based on co-occurrence frequencies, avoiding traditional matrix computations.

Findings

High prediction success rate demonstrated on experimental data

Algorithm has low temporal complexity and does not require transition matrices

Effective clustering of driver trips improves prediction accuracy

Abstract

We present a simple model and algorithm for predicting driver destinations and routes, based on the input of the latest road links visited as part of an ongoing trip. The algorithm may be used to predict any clusters previously observed in a driver's trip history. It assumes that the driver's historical trips are grouped into clusters sharing similar patterns. Given a new trip, the algorithm attempts to predict the cluster in which the trip belongs. The proposed algorithm has low temporal complexity. In addition, it does not require the transition and emission matrices of the Markov chain to be computed. Rather it relies on the frequencies of co-occurrences of road links and trip clusters. We validate the proposed algorithm against an experimental dataset. We discuss the success and convergence of the algorithm and show that our algorithm has a high prediction success rate.