> Per-pair microstructure analytics: realized-volatility modelling with out-of-sample skill, jump shares, cost proxies, and tails. - Canonical: https://hadalinstruments.com/instruments/microstructure-dashboard/ --- [Back to Instruments](https://hadalinstruments.com/instruments/) P6 Feed & Execution # Microstructure Dashboard Bundled inside P1's subscription. Never standalone. Anticipated price Anticipated · not ratified · not an offer Included with the Broker Feed Auditor — never standalone This instrument carries no figure of its own and never will. It ships inside the [Broker Feed Auditor](https://hadalinstruments.com/instruments/broker-feed-auditor/) subscription, anticipated at £149/mo — £1,490/yr on an annual term. Adding it to that subscription changes nothing about the figure. Nothing on this site is on sale. There is no checkout, no cart and no payment link on any page. Prices publish pre-launch so they can be read, compared and checked rather than requested — [seat bands, group licences and multi-year terms are set out in full below](#commercial). here would have added one landmark per placement, which on the homepage means a landmark list that is mostly disclaimer. --> Standing policy — read this beside the figure - **No promise of profit, ever.** Hadal makes no performance claims and carries no implied edge. Past measurements describe instrument behaviour — never future returns. - **You own risk management.** Hadal cannot control it and does not insure it. Good tools do not fix bad discipline — and this site says so. - **Analytical tools, for discretionary use.** Nothing here is investment advice or a recommendation to trade. Every decision, and every outcome, is yours. The same statement stands in the footer of every page.[Terms](https://hadalinstruments.com/terms/) [Privacy](https://hadalinstruments.com/privacy/) [How it measuresThe Feed & Execution suite methodology](https://hadalinstruments.com/methodology/feed/)[BoundsWhat it does not establish](#what-it-does-not-do) Published measurements NOT YET PUBLISHED Specification | Value | Catalogue no. | P6 | Suite | [Feed & Execution](https://hadalinstruments.com/suites/feed/) | Methodology | [How the Feed & Execution suite measures](https://hadalinstruments.com/methodology/feed/) | Availability | Pre-launch — not on sale | Anticipated price | [INCLUDED WITH P1](#anticipated-price) | Delivery | Marketplace SKU · hub subscription | Published measurements | NOT YET PUBLISHED | Provenance artifact | NOT YET PUBLISHED | Most per-pair analytics sold to retail are decoration: a volatility number with no stated model, a session profile with no sample size, a cost estimate nobody has ever checked against a fill. The Microstructure Dashboard is the descriptive layer done properly — every model states its form, every estimate states its sample, and every forecast-shaped output carries its out-of-sample skill beside it. It ships inside the [Broker Feed Auditor](https://hadalinstruments.com/instruments/broker-feed-auditor/) subscription and is never sold standalone. That is a discipline decision rather than a packaging one: microstructure estimates computed on an unaudited feed inherit every defect of that feed, so the dashboard exists only where the fidelity battery has already run. Spread is the part of trading cost that shows on the quote; depth — how much size a pair takes before the price moves — is the part you meet only in the fill, and it reaches this surface as an impact-based cost proxy drawn from the audited feed rather than as a view of the order book. Both are session-dependent rather than fixed properties of a pair: cost, jump share and tail behaviour all move with the session, which is why every quantity here is reported session by session instead of as a single all-hours average. ## What it measures In the subscription, every estimate is computed on your own feed after the Broker Feed Auditor’s battery has run against it. - **Realized volatility, modelled.** HAR-RV over the realized-variance cascade — short, medium and long horizons entering the same model — with out-of-sample skill reported rather than assumed. A volatility model without an out-of-sample number is a curve-fitting exercise wearing a forecast’s clothes. - **Jump and liquidation shares.** The decomposition of variation into its continuous part and its jump part, so the share of a pair’s movement that arrives discontinuously is a measured quantity rather than an impression formed during one bad week. - **Transaction-cost proxies.** Spread- and impact-based cost estimates per pair, computed from the feed itself — a reference point for what trading a pair costs, available before your own statements are imported. - **Tails and session structure.** Tail behaviour of returns, and how every quantity above changes across sessions. The same pair is a different instrument in the Tokyo session and in the London–New York overlap, and the dashboard reports it as two different objects instead of averaging them into one that describes neither. The per-pair estimates publish, each as its own content-hashed artifact: fifty-nine across the liquidity family, thirty-one across session structure, and twenty-eight cross-venue. Skill figures are a different claim and remain **NOT YET PUBLISHED** — an estimate is a measurement of what a pair did, and skill is a claim about predicting it, so the two do not ship on the same receipt and the second one is not owed by the first. ## What the skill figures actually look like A worked reading from my own corpus, so the phrase “out-of-sample skill” has a number attached to it rather than a promise. On EURUSD, the HAR-RV model returns **out-of-sample R² of +40.5% against a random-walk benchmark over 3,834 observations.** Three things about that figure are the reason it is printed here. **It is volatility, not direction.** Realised volatility is among the most forecastable quantities in the field, and return *sign* is among the least. A 40.5% improvement on the former implies precisely nothing about the latter, and an instrument that let the two blur would be trading on the reader’s misunderstanding. **It is out-of-sample against a named benchmark.** “R² = 0.4” in isolation is decoration. Against a random walk, over a stated observation count, on data the model did not see, it is a claim that can be checked. **A poor figure still publishes.** Every pair carries its own skill number, and the ones that do badly are not withheld — a dashboard that only shows its good pairs is a brochure with charts. ## What it does not do The Microstructure Dashboard does not issue signals. Nothing on this surface is a recommendation, a direction or an entry — it is description, and description is the entire claim. It does not forecast price. Where a model produces a forecast-shaped number, its out-of-sample skill is printed beside it precisely so you can judge what that number is worth, and a model with poor skill still publishes, carrying the figure that says so. It also cannot repair a feed: run on a stream that has not passed the fidelity battery, these estimates would faithfully describe the vendor’s artifacts rather than the market, which is exactly why the dashboard is not sold on its own. ## Who it is for Traders who condition sizing, timing or pair selection on how an instrument actually behaves, and who want that behaviour measured on their own audited feed rather than borrowed from a vendor’s marketing chart. ## The ship gate No instrument is sold until it does what this page says it does. Where a page is written in the future tense, that tense is a statement about timing rather than a hedge about capability: the instrument is not finished, so it is not listed as available, not priced as available, and not sold. It waits. Nothing described in this catalogue is a placeholder that will quietly disappear. An instrument that turns out to be wrong gets a [kill-ledger entry](https://hadalinstruments.com/kill-ledger/), not a deletion — which is the only version of that promise anyone can check. ## Commercial terms Published in full, pre-launch, so they can be read and checked rather than requested. Every figure is an anticipated indication I have set and not yet ratified, and every derived figure is the arithmetic of the one above it — shown, not asserted. Nothing here is purchasable: there is no checkout on this site. ### Why Microstructure Dashboard is priced the way it is - **What the figure buys** — Per-pair descriptive analytics computed on a feed the fidelity battery has already audited: realized volatility modelled as HAR-RV across the short, medium and long horizons of the realized-variance cascade, the decomposition of variation into its continuous and jump parts, spread- and impact-based transaction-cost proxies drawn from the feed itself, and tail and session structure reported session by session rather than averaged into one figure. Each forecast-shaped output is designed to carry its out-of-sample skill beside it, including when that figure is unflattering. The boundary is description: no signals, no direction, no entries, no price forecast. The skill figures and per-pair estimates are not yet published, and they ship with the artifacts that prove them rather than ahead of them. - **Why it is priced this way** — There is no separate charge because there is no separate input. Every estimate on this surface is computed from the same stream the Broker Feed Auditor has already run its battery against. Run on a feed that has not passed that battery, the same estimates would faithfully describe the vendor's artifacts rather than the market. Selling it standalone would create a version of the product that can be bought without the thing that makes its numbers mean anything, so that version does not exist. Inclusion here is a discipline decision rather than a packaging one — the dashboard is included as a consequence of the audit because it is one. - **What the alternative costs** — The components are public and you can build them. HAR-RV is a published model, jump decompositions are in the literature, and anyone comfortable with the maths and a data pipeline can implement the lot. What that costs is the pipeline rather than the formulae: clean tick data, session-aware handling so the same pair is not averaged across sessions that behave differently, and an out-of-sample evaluation harness — the piece that is easiest to leave out and the piece that decides whether any forecast-shaped number is worth reading. The free alternative is the volatility readout your platform already shows; it gives you a number, but not the model form, the sample size or the out-of-sample figure you would need to judge it, and doing nothing means sizing, timing and pair selection stay conditioned on impression rather than on a measured distribution. Every figure on this page is an anticipated indication awaiting ratification, and nothing here is purchasable. The reasoning above is published for the same reason the arithmetic below is: a price you can interrogate is worth more than a price you have to accept. ### The two-SKU split Two routes, side by side, with the standing rule rendered as a rule: the hub tier is priced at or below its marketplace equivalent, so the hub is always the better of the two. No marketplace SKU has been listed anywhere yet, so that cell says so instead of showing a figure nobody has set. Route | What it is | Anticipated | Marketplace SKU | Where this instrument ships through a platform marketplace, that SKU is the fully-functional standalone tier — the complete battery, running natively on your platform, no external account required. Never paid-but-crippled. | NOT YET LISTED | Hub subscription (this site) | No SKU of its own, on either route. It is carried inside the Broker Feed Auditor subscription and is never sold standalone — microstructure estimates computed on an unaudited feed inherit every defect of that feed, so the fidelity battery has to have run first. | INCLUDED WITH P1 | The price rule The hub tier is priced at or below its marketplace equivalent. That is a standing rule the pricing table is rendered against, not an offer: a marketplace platform takes a percentage of every sale it processes, and that saving goes to the hub subscriber rather than to Hadal, so a platform fee can never invert your margin. No marketplace SKU has been listed yet, so the cell above reads NOT YET LISTED and the rule stands as a commitment rather than a comparison you can run today. ### Scaling and terms None of its own, and that follows from the instrument rather than from a packaging decision. It has no price, no seat band and no term, because it is not licensed separately at all — the routes and terms that reach it are the [Broker Feed Auditor](https://hadalinstruments.com/instruments/broker-feed-auditor/)’s, in full. ### Commercial routes Pricing scales on the subscription this instrument ships inside — routes, terms and counts are carried there. [Licensing — seat bands, group licences and multi-year terms in full](https://hadalinstruments.com/licensing/) ### Trial mechanics The trial runs on the hub tier — thirty days, a full natural proof cycle, disclosed in plain words before you start it and cancellable in one step; none of it is live yet. [Trial mechanics in full, by delivery class](https://hadalinstruments.com/licensing/#trial). ### Read before you commit The documentation is published ahead of the product on purpose — intended behaviour is only a commitment if it exists first. Start with [installation and first run](https://hadalinstruments.com/docs/install/), then [the limits](https://hadalinstruments.com/docs/limits/): the conditions under which this instrument refuses to produce a number are the part worth reading before you pay. The full centre is at [/docs/](https://hadalinstruments.com/docs/), and the [support model](https://hadalinstruments.com/support/) states what a ticket does and does not cover. ## Questions and answers Answered from what this instrument publishes about itself. Nothing below is attributed to a customer, because there are none yet. ### Can I subscribe to the Microstructure Dashboard on its own? No, and that is a discipline decision rather than a packaging one. Microstructure estimates computed on an unaudited feed inherit every defect of that feed, so the dashboard ships only inside the Broker Feed Auditor subscription, where the fidelity battery has already run. ### Does it issue signals or forecast price? Neither. Nothing on the surface is a recommendation, a direction or an entry — it is description, and description is the entire claim. ### What happens to a model whose out-of-sample skill is poor? The model still publishes, carrying the figure that says so. The skill number sits beside every forecast-shaped output precisely so you can judge what that output is worth. ### Will the Microstructure Dashboard carry a price of its own? No. It is included in the Broker Feed Auditor subscription and is never sold standalone, so it will not have its own line on a pricing table. Nothing on this site is on sale in any case: there is no checkout, no card capture, and no product account to create. ## Change log NOT YET PUBLISHED Microstructure Dashboard has not shipped, so there is nothing to record. When it does, every version lands here — dated, append-only, written by a person, and including the changes that removed a capability rather than added one. ## Where this sits Microstructure Dashboard is one of the instruments in the [Feed & Execution suite](https://hadalinstruments.com/suites/feed/). How that suite measures — the per-instrument battery, and the receipts each measurement will carry — is set out in the [Feed & Execution methodology](https://hadalinstruments.com/methodology/feed/), part of the site-wide [measurement methodology](https://hadalinstruments.com/methodology/). ### Also in the Feed & Execution suite Microstructure Dashboard shares the Feed & Execution suite with two other instruments. - P1 [Broker Feed Auditor](https://hadalinstruments.com/instruments/broker-feed-auditor/) What does your broker's feed actually do when you measure it instead of trusting it? - P9 [Execution Cost Auditor](https://hadalinstruments.com/instruments/execution-cost-auditor/) Statement-import truth about what your execution actually cost. ### Research behind this instrument Microstructure Dashboard draws on six research notes on this site. - [Do brokers hunt your stop losses?](https://hadalinstruments.com/research/do-brokers-hunt-your-stop-losses/) Asked as: "do brokers hunt stop losses by widening the spread" - [Do order blocks predict anything?](https://hadalinstruments.com/research/do-order-blocks-predict-anything/) Asked as: "do order blocks actually predict anything" - [Does a wick rejection mean anything?](https://hadalinstruments.com/research/does-a-wick-rejection-mean-anything/) Asked as: "does a wick rejection actually mean anything" - [Is my volatility regime just telling me the time?](https://hadalinstruments.com/research/is-my-volatility-regime-just-telling-me-the-time/) Asked as: "is my volatility indicator just measuring time of day" - [Why do correlated pairs decouple on low timeframes?](https://hadalinstruments.com/research/why-do-correlated-pairs-decouple-on-low-timeframes/) Asked as: "why do correlated pairs decouple on low timeframes" - [Is my broker trading against me?](https://hadalinstruments.com/research/is-my-broker-trading-against-me/) Asked as: "is my broker trading against me" --- ## Raw artifact — NOT PUBLISHED FOR THIS PAGE No downloadable artifact ships with this page. Eight published measurements do, each content-hashed so a reader can verify the figures independently. Where a measurement is published here without one, that is a gap rather than a policy, and it is stated rather than left to be noticed. [Measurements that ship their data](https://hadalinstruments.com/research/) [Join the launch list](https://hadalinstruments.com/pricing/#waitlist)[How this suite measures](https://hadalinstruments.com/methodology/feed/)