{"paper_id":"2411.16244","title":"What events matter for exchange rate volatility ?","authors":["Igor Martins","Hedibert Freitas Lopes"],"paper_date":"2024-11-25","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.16244v1","page_url":"https://thequant.space/flowcharts/what-events-matter-for-exchange-rate-volatility-/","scores":{"empirical_rigor":6,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper introduces a novel stochastic volatility model that captures announcement effects of hundreds of macroeconomic variables and time‑of‑day patterns for 5‑minute FX returns.","quote":"We introduce a novel stochastic volatility model that captures the announcement effects of hundreds of macroeconomic variables from multiple countries through spike and slab priors, while also accounting for time-of-day patterns.","summary":"This paper expands on stochastic volatility models by proposing a data-driven method to select the macroeconomic events most likely to impact volatility. The paper identifies and quantifies the effects of macroeconomic events across multiple countries on exchange rate volatility using…","strategy":"proposed stochastic volatility model with macro events"},"assumptions":{"status":"available","items":[{"assumption":"The spike component is modeled as a Dirac delta at zero and the slab as a Normal distribution with mean 0.","type":"statistical","stated":"explicit","quote":"We consider the spike to be a Dirac delta at zero and the slab to be a Normal with mean 0 and variance σ2 a."},{"assumption":"The mixing probability πi follows a Beta prior.","type":"statistical","stated":"explicit","quote":"Since γ must be between 0 and 1, we assume a beta prior."},{"assumption":"Seasonality coefficients and AR(1) persistence have normal priors.","type":"statistical","stated":"explicit","quote":"For both the seasonality coefficients and for the persistence of the AR(1) in Equation (3), we assume normal priors."},{"assumption":"Volatility persistence is modeled using stochastic volatility (SV) models rather than GARCH.","type":"model","stated":"explicit","quote":"We choose to model volatility persistence using SV models, given their track record of outperforming GARCH in forecasting volatility."},{"assumption":"5‑minute returns of the Australian Dollar have zero mean.","type":"data","stated":"explicit","quote":"First, the returns have zero mean."},{"assumption":"Macro‑economic announcement timestamps are accurately matched using Bloomberg’s economic calendar and the lubridate package.","type":"data","stated":"explicit","quote":"All timestamps for the macroeconomic announcements are obtained from Bloomberg’s economic calendar. We use the lubridate package"}]},"datasets":{"status":"available","items":[{"name":"Australian Dollar 5‑minute returns","provider":"FirstRate Data","kind":"market-prices","access":"commercial","period":"2017-01-03 to 2023-12-31","universe":"Australian Dollar (AUD) FX spot","quote":"The paper models 5‑minute returns of the Australian Dollar over a 24‑hour period from January 3, 2017, to December 31, 2023, covering 2,554 days."},{"name":"Macro‑economic announcements (US and Australia)","provider":"Bloomberg Economic Calendar","kind":"macro","access":"commercial","period":null,"universe":"117 macro events from Australia and the US","quote":"We consider 117 macroeconomic events from Australia and the US as potential sources of volatility for the Australian Dollar","known_id":"bloomberg"}],"known":[{"id":"bloomberg","name":"Bloomberg","provider":"Bloomberg L.P.","kind":"market-prices","access":"commercial","quote":"All timestamps for the macroeconomic announcements are obtained from Bloomberg’s economic calendar.","mentions":2,"used_in":1}],"sample":{"start":"2017-01","end":"2023-12","market":"Australian Dollar and Swiss Franc","asset_class":"fx","frequency":"intraday"},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"unclear","headline_net_of_costs":false,"detail":null,"quote":null,"source":"conflict","rule":"R4b","candidates":{"front_matter":"no","evidence_card":"n/a","evidence_card_quoted":false},"conflict_kind":"applicability","meaning":"the platform classifier and the paper-text extraction disagree, so no value is asserted"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The proposed model yields the lowest volatility and the highest Sharpe ratio among all models in a global minimum variance portfolio of AUD and CHF.","kind":"performance","quote":"Our model not only yields the smallest volatility but also achieves the highest Sharpe ratio among all models, demonstrating that the selected events have economic implications for investors."},{"finding":"Including macroeconomic events and seasonal components is crucial for forecasting exchange‑rate volatility; competitors are less accurate.","kind":"predictive-accuracy","quote":"We show that including macroeconomic events and seasonal components is crucial for forecasting exchange rate volatility."},{"finding":"Forecast accuracy tests show b1 close to 1 and Diebold‑Mariano p‑values near zero, indicating competitors add little predictive power.","kind":"statistical","quote":"The third row of Table 1 reports the p-values of the test, indicating strong evidence against the null hypothesis of equal forecasting accuracy."},{"finding":"Only announcements related to Taylor‑rule variables have a posterior inclusion probability above 95% for their first lag.","kind":"statistical","quote":"Among hundreds of macroeconomic announcements, the model identifies variables related to the Taylor rule as the only group with over 95% posterior probability of inclusion."},{"finding":"The estimated intraday seasonality effect shows a U‑shaped pattern from 8:00 to 15:00 GMT and an additional U‑shaped pattern from 1:30 to 7:00 GMT.","kind":"statistical","quote":"Consistent with Ito and Hashimoto [2006], we observe a U‑shaped pattern from 8:00 to 15:00 GMT. However,"}],"reported_performance":{"strategy":"proposed stochastic volatility model with macro events","sharpe":0.81,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"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":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"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":"2026-11-14T17:52:26Z"},"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/"}