A novel forecasting framework combining virtual samples and enhanced Transformer models for tourism demand forecasting

2025-03-25

AI Summary

To address the dual challenges of scarce historical data and complex spatiotemporal dependencies in tourism demand forecasting, this paper proposes an end-to-end framework integrating virtual sample generation with an enhanced Transformer architecture. We innovatively design a Spatiotemporal Graph Adversarial Network (ST-GAN) to synthesize high-fidelity virtual time-series sequences; further, we introduce a Transformer variant featuring causal convolution for refined local modeling and non-autoregressive self-attention to effectively capture long-range dependencies. A feedback-driven joint training mechanism is incorporated to enable co-optimization of the generative and predictive modules. Experiments on real-world daily and monthly tourism datasets demonstrate that our method achieves an average 18.37% reduction in Mean Absolute Scaled Error (MASE), significantly improving prediction accuracy and robustness under low-data regimes. This work establishes a novel paradigm for spatiotemporal forecasting with limited observations.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate tourism demand forecasting is hindered by limited historical data and complex spatiotemporal dependencies among tourist origins. A novel forecasting framework integrating virtual sample generation and a novel Transformer predictor addresses constraints arising from restricted data availability. A spatiotemporal GAN produces realistic virtual samples by dynamically modeling spatial correlations through a graph convolutional network, and an enhanced Transformer captures local patterns with causal convolutions and long-term dependencies with self-attention,eliminating autoregressive decoding. A joint training strategy refines virtual sample generation based on predictor feedback to maintain robust performance under data-scarce conditions. Experimental evaluations on real-world daily and monthly tourism demand datasets indicate a reduction in average MASE by 18.37% compared to conventional Transformer-based models, demonstrating improved forecasting accuracy. The integration of adaptive spatiotemporal sample augmentation with a specialized Transformer can effectively address limited-data forecasting scenarios in tourism management.

Problem

• Overcoming limited historical data in tourism demand forecasting
• Modeling complex spatiotemporal dependencies among tourist origins
• Improving forecasting accuracy with virtual samples and enhanced Transformer

Innovation

• Virtual sample generation via spatiotemporal GAN
• Enhanced Transformer with causal convolutions
• Joint training strategy for robust performance