{"paper_id":"2508.19609","title":"FinCast: A Foundation Model for Financial Time-Series Forecasting","authors":["Zhuohang Zhu","Haodong Chen","Qiang Qu","Vera Chung"],"paper_date":"2025-08-27","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.19609v1","page_url":"https://thequant.space/flowcharts/fincast-a-foundation-model-for-financial-time-series-foreca/","scores":{"empirical_rigor":8.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes FinCast, a foundation model for financial time-series forecasting.","quote":"To address the limitations of existing approaches, we introduce FinCast, a foundation model for financial time-series forecasting.","summary":"Financial time-series forecasting is critical for maintaining economic stability, guiding informed policymaking, and promoting sustainable investment practices. However, it remains challenging due to various underlying pattern shifts. These shifts arise primarily from three sources: temporal…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A large-capacity model trained on sufficiently diverse and large-scale financial data can learn a broad spectrum of temporal patterns, domain-specific dynamics, and resolution-dependent behaviors.","type":"model","stated":"implied","quote":"Intuitively, a large-capacity model, trained on sufficiently diverse and large-scale financial data, can learn a broad spectrum of temporal patterns, domain-specific dynamics, and resolution-dependent behaviors."},{"assumption":"Point-Quantile loss enhances robustness to temporal shifts and prevents forecast collapse.","type":"model","stated":"implied","quote":"First, Point-Quantile loss (PQ-loss), which jointly optimizes point forecasts and quantile-based probabilistic estimates to model uncertainty across the distribution, enhances robustness to temporal shifts and prevents forecast collapse."},{"assumption":"Token-level sparse Mixture-of-Experts increases capacity efficiently and enables expert specialization across domains.","type":"model","stated":"implied","quote":"Second, a token-level sparse Mixture-of-Experts (MoE) mechanism that increases capacity efficiently and enables experts to specialize across domains."},{"assumption":"Financial data obtained from public APIs is of sufficient quality after cleaning to train the model.","type":"data","stated":"implied","quote":"All financial data is obtained through publicly accessible interfaces and APIs."},{"assumption":"Zero-shot performance can be evaluated without any task-specific fine‑tuning.","type":"execution","stated":"explicit","quote":"FinCast consistently outperforms state-of-the-art methods across both zero-shot and supervised financial forecasting benchmarks, achieving best results without task-specific fine-tuning."}]},"datasets":{"status":"available","items":[{"name":"Pretraining dataset","provider":null,"kind":"market-prices","access":"public","period":null,"universe":"cryptocurrency, forex, futures, stocks, macroeconomic indicators and others","quote":"We create a comprehensive pretraining dataset with 20 billion time points across multiple financial and non-financial domains, encompassing a wide range of temporal frequencies from seconds to months."},{"name":"Zero-shot benchmark dataset","provider":null,"kind":"benchmark","access":"unknown","period":null,"universe":null,"quote":"To evaluate zero-shot performance, we introduce a benchmark dataset comprising 3,632 time series and over 4.38 million scalar time points."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"FinCast consistently outperforms state-of-the-art methods across both zero-shot and supervised financial forecasting benchmarks, achieving best results without task-specific fine-tuning.","kind":"performance","quote":"FinCast consistently outperforms state-of-the-art methods across both zero-shot and supervised financial forecasting benchmarks, achieving best results without task-specific fine-tuning."},{"finding":"FinCast achieves on average 20% lower MSE in zero-shot settings compared to existing SOTA methods.","kind":"performance","quote":"FinCast achieves on average 20% lower MSE in zero-shot settings compared to existing SOTA methods."},{"finding":"Performance gain, reducing MSE by 23% and MAE by 16% on average; fine‑tuning further reduces MSE and MAE by 26% and 19% respectively.","kind":"performance","quote":"performance gain, reducing MSE by 23% and MAE by 16% on average. The performance further improves with fine-tuning, yielding 26% and 19% reductions in MSE and MAE, respectively."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/vincent05r/FinCast-fts","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:28:54Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}