Recovering Individual-Level Activity Sequences from Location-Based Service Data Using a Novel Transformer-Based Model

Word Count: 6, 279 words + 3 table (250 words per table) = 7, 029 words Submitted [ 08/01/2025 ] *Corresponding Author Weiyu Luo, Chenfeng Xiong 2 ABSTR A CT Location - Based Service (LBS) data provides critical insights into human mobility, yet its sparsity often yields incomplete trip and activity sequences, making accurate inferences about trips and activities difficult . We raised a research problem: Can we use activity sequences derived from high - quality LBS data to recover incomplete activity sequences at individual level? This study proposes a new solution, the Variable Selection Network - fused Insertion Transformer (VSNIT), integrating the Insertion Transformer ' s flexible sequence construction with the Variable Selection Network's dynamic covariate handling capability, to recover missing segments in incomplete activity sequences while preserving existing data . The findings show that VSNIT inserts more diverse, realistic activity patterns, more closely matching real - world variability, and restores disrupted activity transiti ons more effectively aligning with the target. It also performs significantly better than the baseline model across all metrics. These results highlight VSNIT ' s superior accuracy and diversity in activity sequence recovery tasks, demonstrating its potential to enhance LBS data utility for mobility analysis. This approach offers a promising framework for future location - based research and applications. Keywords: Sequence - To - Sequence Modeling, Location - Based - Service Data, Data Spar sity, Insertion Transformer, Activity - Based M odeling, Human Mobility Weiyu Luo, Chenfeng Xiong 3 INTRODUCTION Activity - based model Activity - based modeling (ABM) emerged in response to the limitations of traditional trip - based models, providing a more behaviorally appropriate framework for understanding travel demand ( 1 - 3) .