HINTS: Extraction of Human Insights from Time-Series Without External Sources
This addresses the high data dependency costs in financial and economic forecasting for practitioners, though it appears incremental as it builds on existing backbone models.
The paper tackles the problem of capturing human factors in time-series forecasting without relying on costly external data sources by proposing HINTS, a self-supervised framework that extracts latent human factors from time-series residuals using opinion dynamics models, which improved forecasting accuracy across nine real-world and benchmark datasets.
Human decision-making, emotions, and collective psychology are complex factors that shape the temporal dynamics observed in financial and economic systems. Many recent time series forecasting models leverage external sources (e.g., news and social media) to capture human factors, but these approaches incur high data dependency costs in terms of financial, computational, and practical implications. In this study, we propose HINTS, a self-supervised learning framework that extracts these latent factors endogenously from time series residuals without external data. HINTS leverages the Friedkin-Johnsen (FJ) opinion dynamics model as a structural inductive bias to model evolving social influence, memory, and bias patterns. The extracted human factors are integrated into a state-of-the-art backbone model as an attention map. Experimental results using nine real-world and benchmark datasets demonstrate that HINTS consistently improves forecasting accuracy. Furthermore, multiple case studies and ablation studies validate the interpretability of HINTS, demonstrating strong semantic alignment between the extracted factors and real-world events, demonstrating the practical utility of HINTS.