analiza aiqbench
HARN introduces a novel architecture for financial time series forecasting that efficiently handles multi-timeframe data by updating representations only when new information arrives. This approach combines causal encoding with associative memory mechanisms to compete with established baselines like PatchTST while maintaining computational efficiency through event-driven updates. The study emphasizes architectural consistency and component ablation over claims of universal predictive superiority, offering a practical framework for handling complex temporal resolutions in asset markets.
HARN: Hierarchical Associative Resonance Network for Event-Driven Multi-Timeframe Forecasting
arXiv:2609.26822v1 Announce Type: new Abstract: Financial time series evolve across multiple temporal resolutions, challenging forecasting systems to incorporate newly available information without repeatedly recomputing unchanged representations. We introduce HARN, a Hierarchical Associative Resonance Network for event-driven multi-timeframe forecasting. HARN maintains persistent representations across temporal levels and updates each level only when its corresponding completed bar becomes available. The architecture combines causal multi-scale temporal encoding, gated associative memory, cross-level resonance, and hierarchical evidence aggregation, with forecasting performed in basis-point space and reconstructed to the original price scale. We evaluate HARN on four assets spanning equity, foreign exchange, and commodity markets using multiple random seeds and component ablations. HARN achieves competitive reconstructed-price forecasting errors against single-timeframe PatchTST and TimeXer baselines, while ablations reveal the effects of removing individual components across assets and timeframes. A code-level audit further examines consistency between the implementation and the defined event-driven causal protocol. The results position HARN as a persistent multi-timeframe forecasting framework rather than evidence of universal predictive superiority.
Abstract:Financial time series evolve across multiple temporal resolutions, challenging forecasting systems to incorporate newly available information without repeatedly recomputing unchanged representations. We introduce HARN, a Hierarchical Associative Resonance Network for event-driven multi-timeframe forecasting. HARN maintains persistent representations across temporal levels and updates each level only when its corresponding completed bar becomes available. The architecture combines causal multi-scale temporal encoding, gated associative memory, cross-level resonance, and hierarchical evidence aggregation, with forecasting performed in basis-point space and reconstructed to the original price scale. We evaluate HARN on four assets spanning equity, foreign exchange, and commodity markets using multiple random seeds and component ablations. HARN achieves competitive reconstructed-price forecasting errors against single-timeframe PatchTST and TimeXer baselines, while ablations reveal the effects of removing individual components across assets and timeframes. A code-level audit further examines consistency between the implementation and the defined event-driven causal protocol. The results position HARN as a persistent multi-timeframe forecasting framework rather than evidence of universal predictive superiority.
Machine Learning (cs.LG); Computational Finance (q-fin.CP); General Finance (q-fin.GN)
arXiv:2609.26822 [cs.LG]
(or arXiv:2609.26822v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.26822 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 256 cuvinte
Subiecte conexe
Netskope (NTSK) Q2 2027 Earnings Call Transcript
fool.com · 10 sept. 2026
News
Quantum Computing Report · 25 iul. 2026
Building Blocks for Foundation Model Training and Inference on AWS
Hugging Face · 11 mai 2026
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta Engineering · 3 aug. 2026