A Prompt Refinement-based Large Language Model for Metro Passenger Flow Forecasting under Delay Conditions

TL;DR

This paper introduces a novel prompt refinement framework leveraging large language models to improve short-term metro passenger flow forecasting during delays, addressing data scarcity and complex delay impacts.

Contribution

The study proposes a prompt engineering approach that enhances LLMs' ability to forecast passenger flow under delay conditions with minimal data, a novel application in transit systems.

Findings

The framework achieves high accuracy in real-world Shenzhen metro data.

Prompt refinement significantly improves forecasting performance.

The approach effectively handles rare delay events.

Abstract

Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched. Due to the rare occurrence of delay events, the limited sample size under delay condictions make it difficult for conventional models to effectively capture the complex impacts of delays on passenger flow, resulting in low forecasting accuracy. Recognizing the strengths of large language models (LLMs) in few-shot learning due to their powerful pre-training, contextual understanding, ability to perform zero-shot and few-shot reasoning, to address the issues that effectively generalize and adapt with minimal data, we propose a passenger flow forecasting framework under delay conditions that synthesizes an LLM with carefully designed prompt engineering. By Refining prompt design, we enable the LLM to understand delay event information and the pattern from historical passenger flow data, thus overcoming the challenges of passenger flow forecasting under delay conditions. The propmpt engineering in the framework consists of two main stages: systematic prompt generation and prompt refinement. In the prompt generation stage, multi-source data is transformed into descriptive texts understandable by the LLM and stored. In the prompt refinement stage, we employ the multidimensional Chain of Thought (CoT) method to refine the prompts. We verify the proposed framework by conducting experiments using real-world datasets specifically targeting passenger flow forecasting under delay conditions of Shenzhen metro in China. The experimental results demonstrate that the proposed model performs particularly well in forecasting passenger flow under delay conditions.