A human-centric machine learning based personalized route choice prediction in navigation systems

Abstract

Real-world route navigation data indicate that nontrivial portion of drivers do not prefer the system-recommended best routes. Current navigation systems have simplified assumptions about drivers’ route choice preferences and do not adequately accommodate drivers’ heterogeneous route choice preferences, mainly because of: (i) difficulty in acquiring exogenous criteria (e.g., sociodemographic information) that are typically used to differentiate drivers’ preferences in behavioral modeling; and (ii) difficulty in capturing preference of individuals due to limited preference data at the individual level. To address these, this paper introduced a human-centric machine learning technique named Multi-Task Linear Classification Model Adaption (MT-LinAdapt). It can capture drivers’ common aspects of route choice preferences and yet adapts to each driver’s own preference. In addition, any evolvement of individual drivers’ preferences can be simultaneously integrated to update the common preference for further individual drivers’ preference adaptation. This paper evaluated MT-LinAdapt against two state-of-the-art route recommendation strategies including an aggregate-level and an individual-level data-based strategies, which are categorized based on the data used for modeling. With a real-world dataset containing 30,837 drivers’ navigation usage data in Daegu City, South Korea, MT-LinAdapt was compared to existing strategies for its performance at different levels of data availability, and showed at least the same performance with existing strategies when minimum preference data is available and achieves up to 7% higher prediction accuracy as more data becomes available. Higher prediction accuracies are expected to bring better user satisfaction and compliance rates which can further help with transportation system control and management strategies.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.