ATLAS

Adaptive Tactical & Long-Horizon Allocation System

A regime-aware decision-support system for managing portfolio exposure under uncertainty — multitenant, governance-first, and designed so that abstention is a legitimate output, not a missing answer.

Try the Demo Login

Self-Service Demo

Explore ATLAS with sample portfolio data in a sandboxed demo environment. No account required. Demo sessions use delayed market data and include no live portfolio information.

Launch Demo →

What ATLAS Is

ATLAS is a portfolio governance and macro-regime monitoring system designed to help investors manage exposure to uncertainty in global markets.

Rather than attempting to predict short-term price movements, ATLAS focuses on detecting structural regime shifts, systemic stress, and instability across financial markets. The system integrates multiple cross-asset signals to evaluate whether conditions favor risk-taking, caution, or abstention.

ATLAS is designed around a central principle: managing exposure to uncertainty is more important than maximizing returns during unstable regimes.

What ATLAS Is Not

  • ATLAS is not a trading bot.
  • ATLAS does not generate buy/sell signals.
  • ATLAS does not attempt to predict short-term market movements.
  • ATLAS does not optimize portfolios or chase alpha.

Instead, the system provides a structured framework for evaluating macroeconomic conditions and portfolio alignment across regimes.

Built for Governed, Multitenant Decision Support

ATLAS is built as a multitenant platform from the ground up. Every artifact, view, and decision surface is associated with an explicit tenant and operator context, so what one operator sees, exports, or acts on is scoped, attributable, and isolated from the rest of the system.

  • Tenant-aware architecture. Decision artifacts, portfolio state, and analytics surfaces carry tenant identity end-to-end. Cross-tenant access is structurally prevented, not merely filtered.
  • Operator-scoped views. Each operator sees only the sleeves, portfolios, and decision context they are entitled to. Overrides, edits, and acknowledgements are attributed and logged.
  • Admin-only isolation. Administrative surfaces — entitlements, governance configuration, system-wide exports — are separated from tenant-visible surfaces and never bleed into the operator UI.
  • Provenance and freshness. Outputs carry as-of timestamps, source attribution, and freshness status. Stale, degraded, and unavailable states are surfaced explicitly rather than papered over.
  • Abstention-aware portfolio governance. When the system is uncertain, that uncertainty is part of the answer. Abstention, transitional, and indeterminate states are first-class outputs that route through the same governance surfaces as any other decision.
  • AI summaries grounded in machine-readable state. Natural-language summaries explain a structured, governed state object. They do not generate decisions, override gates, or substitute for the system of record.

Capabilities

Structural Regime Classification

Classification of prevailing macro conditions from a cross-asset signal set, with confidence measurement, persistence analysis, and stability diagnostics. Designed to be slow-moving and interpretable.

Tactical Instability Engine

Fail-closed detection of deteriorating classification certainty, producing persistence-aware decision states — Allocate, Reduce, and Abstain — with hysteresis controls to prevent flicker.

Abstention Governance

Abstention treated as a first-class decision output with a defined episode lifecycle, post-hoc outcome evaluation, trigger attribution, and regime-conditioned economic accounting.

SENTINEL Structural Forecasting

Multi-horizon regime-transition diagnostics, including flip probability estimation, hazard-rate modeling, and persistence analysis. Published as a research-grade diagnostic signal; not coupled to exposure policy.

Separation & Integrity

Continuous monitoring of decoupling between structural and tactical layers, with leakage detection, contamination audits, and tiered escalation. Ensures fast signals do not contaminate slow ones.

Portfolio Management

Multi-broker position ingest, exposure decomposition, concentration and regime-alignment analysis, target generation, and sleeve-scoped governance of proposed changes.

GitPortfolio

Version-controlled portfolio workflow with change history, merge governance, counterfactual replay under alternative regime paths, and auditable experimentation with hypothesis tracking.

Optionality Insurance

Tail-protection workflow with premium budgeting, ladder construction, gap reconciliation, and position reconciliation. Protection cost is reported as an estimate proxy; real option-chain pricing is deferred.

Governance Measurement

Artifact freshness validation with canonical signature tracking, calibration and horizon-sensitivity audits, robustness stress testing, and full pipeline provenance logging.

Learning & Policy Lab

Hypothesis registry with shadow-mode evaluation and promotion gating. Evidence-velocity tracking, scenario comparison, and validation requirements before any candidate change enters governance.

Explanation & Transparency

Layered explanation of each decision across structural, tactical, constraint, and availability dimensions, with gated disclosure of implications (allowed, qualified, or withheld).

Multi-Operator Isolation

Operator-scoped governance with isolated override state, per-operator sleeve management, composite-key entitlements, operator-aware audit trails, and fail-closed tenancy enforcement.

Access Control & Audit

OIDC authentication, sleeve-based authorization with group mapping, entitlement system, full decision audit trail, override accounting, and governance logging.

Decision Economics Unification

Single-pass diagnostic baseline joining decisions, NAV-denominated realized economics, regime context, forward evidence, and posture flags. Provides an auditable end-to-end view of decision history and outcomes; runs as a measurement reference, not as allocation authority.

Truthfulness Contract

Decision-facing surfaces declare their evidence basis explicitly via decision-support and evidence-posture badges (live governance, shadow replay, diagnostic model, or insufficient). Per-layer registry enforces that no panel renders an implicit claim; missing inputs surface as labeled states, not silent fallbacks.

In Development

  • Universal truthfulness wiring across all remaining decision-facing surfaces
  • Operator self-serve onboarding and sleeve-provisioning workflow
  • Pipeline observability module and sleeve-health UX surfacing
  • Candidate signal evaluation under credible-null promotion discipline
  • Further automation of separation-layer escalation

Why ATLAS Exists

Most investment systems focus on maximizing returns under stable market conditions. ATLAS is designed for the opposite problem: navigating periods when markets become unstable, regimes shift, and traditional assumptions break down.

By emphasizing regime awareness, uncertainty management, and abstention as a legitimate decision state, ATLAS provides a framework for disciplined portfolio governance across changing macro environments.

Development Status

ATLAS is in active production with continuous development. The production environment delivers governance-grade regime monitoring, portfolio management, and operator-isolated decision tooling. The beta environment provides access to experimental features and ongoing system improvements.

Pricing

For pricing inquiries, institutional licensing, and operator onboarding, please visit the Contact page.

Updates

Release notes and development milestones


May 2026

Production Update — Decision Ledger, Surface Honesty & Calibrated Caution

A production update is live at app.atlas-portal.ca. The release sharpens how ATLAS represents what it knows, what it does not know, and how the platform talks to operators about both.

  • Unified decision ledger. Decisions, realized economics, regime context, and forward evidence now live behind a single auditable surface, so that the end-to-end story of any decision — from input artifact to outcome — can be reviewed in one place. The unified ledger is a measurement and audit reference; it has no allocation authority of its own.
  • Surface-level truthfulness. Decision-facing panels now declare their evidence basis explicitly, indicating whether a view is backed by live governance, a shadow replay, a diagnostic model, or insufficient evidence. Missing or stale inputs surface as labeled states rather than silent fallbacks.
  • Calibrated caution. The platform now maps measurement-uncertainty states to a graduated, minimal-response policy. Where the system cannot yet make a confident statement, it says so, and the appropriate degree of caution is recorded against the abstention ledger for outcome evaluation.
  • Research discipline for new strategy contexts. Candidate trend and momentum strategy contexts are now tracked through a formal evidence dossier — forward evidence, reconstructed historical evidence, and live-portfolio context — before any promotion into governance. Authorization gates are explicit and time-bound; nothing promotes itself by default.
  • Adversarial review of decision-facing surfaces. A broad audit was run across the platform’s advisory and shadow surfaces, looking specifically for ways a panel could imply a claim it could not back. Findings were closed before the release shipped.
  • Operator-visible pipeline state. Pipeline telemetry, run health, and tenant-aware run identifiers are now consistently visible across observability surfaces, so operators can tell at a glance whether what they are reading is current, partial, or stale.
April 2026

Production Update — Multi-Operator Governance, Pipeline Reliability & Structural Forecasting

A major production update is now live at app.atlas-portal.ca. The release brings ATLAS’s multitenant governance posture, pipeline reliability, and structural forecasting capabilities to production grade.

  • Multi-operator governance. Operator and sleeve identity now flow end-to-end through the platform. Overrides, audit trails, entitlements, and portfolio visibility are isolated by operator context, so each operator sees and acts on only their own scope.
  • Structural forecasting in production. Regime flip-probability estimation, persistence modeling, and hazard-rate diagnostics are now operational in production across multiple forward horizons. Forecasts are surfaced as diagnostic context, separated from exposure policy.
  • Forecast calibration. A dedicated calibration artifact now measures how well structural forecasts have matched realized outcomes across horizons, so the platform can be honest about where its forecasts have been reliable and where they have not.
  • Fail-fast pipeline. The pipeline now validates governance readiness, configuration, and stage prerequisites before expensive computation begins. Problems surface immediately at startup rather than late in a run.
  • One source of truth for abstention. Abstention state was consolidated behind a single authoritative source feeding both the UI and portfolio gating, eliminating the possibility of disagreement between views.
  • More robust portfolio ingest. Multi-file upload handling, timestamp safety, and collation were hardened, reducing operator friction during portfolio refreshes.
  • Forecast observatory. Structural-transition surfaces, horizon-specific transition probabilities, and forecast diagnostics now render consistently across the operator UI.
  • Abstention economics. Regime-conditioned breakdowns and the abstention economics panel were restored, including episode outcome classification and false-caution tracking by regime.
  • Sleeve-scoped optionality. The optionality view is now strictly scoped to the selected sleeve, with no silent fallback to an aggregate view when sleeve context is missing.
  • Production infrastructure. Entitlements infrastructure was modernized with automated migration and operator backfill, provenance guarding was added for containerized runs, and deployment tooling was extended to support the multitenant production surface.
March 26, 2026

Beta v2 — Regime-Conditioned Model, GitPortfolio & Forecasting

A new beta version is now available at beta.atlas-portal.ca incorporating significant new capabilities:

  • Regime-Conditioned Model — Portfolio analytics and risk assessments are conditioned on the current detected macro regime.
  • GitPortfolio — Live portfolio replay and counterfactual analysis. Track how portfolio decisions would have played out under alternative regime paths and allocation strategies.
  • Forecasting — Forward-looking regime-transition probability modeling and macro-forecasting tools for scenario planning and exposure management.
March 16, 2026

Site Launch — Cross-Asset Regime Model

ATLAS Portal is live. The initial release introduces the core cross-asset regime classification model — a system for detecting structural regime shifts, systemic stress, and instability across global financial markets.

  • Cross-asset regime classification and confidence scoring
  • Multi-signal macro stress monitoring
  • Regime flip-risk estimation and transition probability modeling
  • Portfolio exposure alignment diagnostics
  • Institutional-grade audit logging and governance tooling

Technical Specification

Formal model objects, governance, and admissible decision rules


1. System Object

ATLAS is specified as a tuple of measurable and governed objects. Every component is defined in the sections that follow with its domain, role, and admissible use.

\[ \mathcal{A}_{ATLAS} \;=\; \big(\mathcal{X},\, \mathcal{D},\, \mathcal{G},\, \mathcal{S},\, \mathcal{T},\, \mathcal{C},\, \mathcal{F},\, \Pi,\, \mathcal{V}\big) \]
  • \(\mathcal{X}\) — observable state space (cross-asset, regime-scoring inputs)
  • \(\mathcal{D}\) — governed artifact space (schema-validated, provenance-tracked outputs)
  • \(\mathcal{G}\) — governance / data-quality state space (admissibility of \(\mathcal{D}\))
  • \(\mathcal{S}\) — structural regime state space (finite, slow, persistent)
  • \(\mathcal{T}\) — tactical instability state space \(\{\text{Stable},\, \text{Transitional},\, \text{Unstable}\}\)
  • \(\mathcal{C}\) — confidence / boundary-distance space
  • \(\mathcal{F}\) — flip-risk / transition-pressure space
  • \(\Pi\) — admissible policy map (Section 8)
  • \(\mathcal{V}\) — validation operator family (Section 10)

ATLAS is a measurement and decision-governance system. It is not a return forecaster, an unconstrained optimizer, or an execution engine. Sections 2–14 define each component formally; Sections 15–16 give the public glossary and the explicit non-claims.

1.1 Standing Assumptions

All random variables in this document are defined on a fixed probability space \((\Omega, \mathcal{H}, \mathbb{P})\) equipped with the discrete-time filtration \((\mathcal{F}_t)_{t \in \mathbb{Z}_{\ge 0}}\) introduced in Section 2. Statements of equality involving random variables are understood \(\mathbb{P}\)-almost surely; statements of equality involving deterministic objects are absolute.

The remainder of the document operates under the following labeled assumptions. Each is stated as part of the specification, not asserted as universally true of the underlying market or of the data-generating process.

  • A1 (Finite latent state). The structural regime takes values in a finite set, \(|\mathcal{S}| < \infty\), and evolves as a Markov chain with transition matrix \(P\) (Section 3).
  • A2 (Information adaptation). All decision-time objects — \(S_t,\, T_t,\, C_t,\, F_t,\, D_t^{\,score},\, \pi_t\) — are \(\mathcal{F}_t\)-measurable, where \(\mathcal{F}_t\) is the natural artifact filtration introduced in Section 2.
  • A3 (Fail-closed tactical layer). Inputs that are NA-driven or whose governing artifacts are inadmissible cannot resolve to \(T_t = \text{Stable}\) (Section 4).
  • A4 (Deterministic validation). Each validator \(V_j\) is a deterministic function on artifact contracts (Section 10).
  • A5 (Closed-set authorization). The authorization predicate \(\operatorname{Auth}(o, s, r)\) is two-valued (Section 11).

Assumptions A1–A5 are referred to by label where their force is invoked.

2. Observation and Artifact Layer

Let \(t\) denote decision time and \(d\) an observation date. Let \(X_t \in \mathcal{X}\) denote the observable state vector and \(\mathcal{D}_t\) the set of artifacts available at \(t\):

\[ \mathcal{D}_t \;=\; \{D_{1,t},\, D_{2,t},\, \ldots,\, D_{m,t}\} \]

For each artifact define its maximum observation date and lag:

\[ d_i^{\max}(t) \;=\; \max\,\{ d : D_{i,t}(d) \text{ exists}\}, \qquad \ell_i(t) \;=\; t - d_i^{\max}(t) \]

Artifact state is a closed-set label:

\[ q_i(t) \;\in\; \{\mathrm{OK},\, \mathrm{STALE},\, \mathrm{DEGRADED},\, \mathrm{UNAVAILABLE},\, \mathrm{INSUFFICIENT}\} \]

Eligibility for downstream use admits labeled states (OK, STALE, DEGRADED) and blocks the two value-less states (UNAVAILABLE, INSUFFICIENT):

\[ E(D_{i,t}) \;=\; \mathbf{1}\!\big\{\, \mathrm{schema}(D_i)=1 \,\land\, \mathrm{keys}(D_i)=1 \,\land\, \mathrm{dates}(D_i)=1 \,\land\, q_i(t) \,\in\, \{\mathrm{OK},\, \mathrm{STALE},\, \mathrm{DEGRADED}\} \,\big\} \]

A STALE or DEGRADED artifact carries its label downstream rather than being silently substituted; an UNAVAILABLE or INSUFFICIENT artifact has no value to consume, and downstream computations fail closed (Section 10).

The natural artifact filtration is the increasing family of \(\sigma\)-algebras

\[ \mathcal{F}_t \;=\; \sigma\!\Big(\,\big\{\, D_{i,\,t}(d) \,:\, E(D_{i,\,t}) = 1,\;\; d \le t,\;\; i \in I_t\,\big\}\,\Big), \qquad \mathcal{F}_s \;\subseteq\; \mathcal{F}_t \quad (s \le t) \]

where \(I_t\) is the set of artifact indices available at \(t\). By Assumption A2, every decision-time object defined in Sections 3–8 is \(\mathcal{F}_t\)-measurable: ATLAS cannot use information that is not in \(\mathcal{F}_t\), and any apparent use of such information is a governance violation.

Stale-state truthfulness. Define a current-day-complete artifact as one with \(\ell_i(t) = 0\) and \(q_i(t) = \mathrm{OK}\); a latest-available artifact as one with \(\ell_i(t) \ge 0\) and \(q_i(t) \in \{\mathrm{OK}, \mathrm{STALE}, \mathrm{DEGRADED}\}\). The two are not the same object; the latter must carry its label. Absence of data is not evidence of stability: \(q_i(t) = \mathrm{UNAVAILABLE}\) does not imply \(T_t = \text{Stable}\) (in fact, by A3, it forbids it). Artifacts are the measurement substrate from which all downstream objects in \(\mathcal{S}\), \(\mathcal{T}\), \(\mathcal{C}\), \(\mathcal{F}\), and \(\Pi\) are derived.

In the live implementation, \(q_i\) is decomposed into three orthogonal axes — a freshness label (timeliness and calendar-completeness), a health label (input quality), and an observability label (sample sufficiency for derivative quantities) — treated as governance vocabulary rather than analytic detail. The closed set above is the public abstraction.

3. Structural Regime

The structural regime \(S_t \in \mathcal{S}\) is a finite-valued classification of the prevailing macro environment. Let \(Z_t = (Z_{1,t}, \ldots, Z_{k,t})\) denote a low-dimensional vector of governed scores along the growth, inflation, risk-appetite, and liquidity axes. Then

\[ f_S \,:\, \textstyle\bigcup_{T \ge 1} (\mathbb{R}^k)^T \,\times\, \Theta_S \,\times\, \mathcal{G} \;\longrightarrow\; \mathcal{S}, \qquad S_t \;=\; f_S\!\big(Z_{1:t},\, \Theta_S,\, G_t\big), \qquad |\mathcal{S}| < \infty \]

\(\Theta_S\) denotes the governed structural parameters; \(G_t\) is the artifact-admissibility state at time \(t\). The map \(f_S\) is stateful (the argument is the score history \(Z_{1:t}\), not \(Z_t\) alone); slowness and persistence of the resulting state sequence are formalized by the inequality below. Structural-regime estimation is in the regime-switching tradition (Hamilton, 1989), in which the latent state evolves as a Markov chain with transition matrix

\[ P \;\in\; [0,\, 1]^{|\mathcal{S}| \times |\mathcal{S}|}, \qquad P_{ij} \;=\; \mathbb{P}\!\big(S_{t+1} = j \,\big|\, S_t = i\big), \qquad \sum_{j} P_{ij} \;=\; 1 \;\;\forall\, i \]

The diagonal \(P_{ii}\) is the one-step self-persistence of regime \(i\); the off-diagonal mass governs reachability between regimes. \(P\) is a member of \(\Theta_S\) and is estimated on a declared calibration window (Section 14).

Structural regime is not tactical instability:

\[ S_t \;\not\equiv\; T_t, \qquad \mathbb{P}(S_{t+h} = S_t) \;\gg\; \mathbb{P}(T_{t+h} = T_t) \]

\(T_t\) does not appear as an argument of \(f_S\); equivalently, \(S_t\) is \(\sigma(Z_{1:t}, \Theta_S, G_t)\)-measurable and not \(\sigma(T_t)\)-measurable in general. A single-layer model that conflates the two horizons violates the persistence inequality above (Ang & Timmermann, 2012). Separation is monitored by the leakage diagnostic \(\mathrm{lk}(W) = I(S_t; T_t \mid Z_t)\) of Section 12 (HEDGEHOG).

4. Tactical Instability

The tactical state \(T_t \in \{\text{Stable},\, \text{Transitional},\, \text{Unstable}\}\) is derived from high-frequency diagnostics of classification certainty. Define discrete differences:

\[ \Delta x_t \;=\; x_t - x_{t-1}, \qquad \Delta^2 x_t \;=\; x_t - 2x_{t-1} + x_{t-2} \]

The tactical objects are:

  • \(H_t\) — transitional severity (integer-valued)
  • \(N_t\) — NA-driven indicator (logical)
  • \(K_t\) — trigger count (integer-valued)
  • \(C_t,\ \Delta C_t\) — confidence and confidence change (Section 5)
  • \(F_t,\ \Delta^2 F_t\) — flip-risk and flip-risk acceleration (Section 6)

The tactical fusion is

\[ f_T \,:\, \mathcal{F} \,\times\, \mathbb{R} \,\times\, \mathcal{C} \,\times\, \mathbb{R} \,\times\, \{0,1\} \,\times\, \mathcal{G} \;\longrightarrow\; \mathcal{T}, \qquad T_t \;=\; f_T\!\big(F_t,\, \Delta^2 F_t,\, C_t,\, \Delta C_t,\, N_t,\, G_t\big) \]

Thresholds and parameter values within \(\Theta_T\) are not disclosed. The fail-closed invariant is stated as an implication:

\[ N_t = 1 \;\;\lor\;\; G_t = \mathrm{INADMISSIBLE} \quad\Longrightarrow\quad T_t \,\in\, \{\text{Transitional},\, \text{Unstable}\} \]

Equivalently: a tactical input that is NA-driven or whose governing artifacts are inadmissible can never resolve to Stable. The structural-tactical separation invariant — \(T_t\) does not appear as an argument of \(f_S\) (Section 3) — is enforced by construction. Any structural override is the subject of a separately governed rule, never implicit in tactical motion.

5. Confidence as Boundary Distance

Confidence \(C_t \in \mathcal{C}\) is defined as proximity to a decision boundary (Bishop, 2006, Ch. 4), not as subjective belief. Let \(M_s : \mathbb{R}^k \to \mathbb{R}\) denote the score/margin function assigned to structural state \(s\). The live confidence object is the score-margin form:

\[ C_t \;=\; \min_{s \neq s'}\, \big|\, M_s(Z_t) - M_{s'}(Z_t) \,\big| \;\in\; [0,\, \infty) \]

Let \(\Gamma \subset \mathbb{R}^k\) denote the structural decision boundary — under the margin form, the indifference locus \(\Gamma = \{\,z \in \mathbb{R}^k \,:\, M_s(z) = M_{s'}(z) \text{ for some } s \neq s'\,\}\); under the geometric form, an estimated surface in the score space. A geometric distance formulation

\[ d(Z_t,\, \Gamma) \;=\; \inf_{g \,\in\, \Gamma}\, \| Z_t - g \| \]

is computed in a shadow geometry layer as a research-only diagnostic and does not gate live policy. In both formulations, the boundary limit

\[ C_t \,\downarrow\, 0 \quad \text{as} \quad Z_t \,\to\, \Gamma \]

holds by construction. Both \(C_t\) and \(\Delta C_t\) are first-class \(\mathcal{F}_t\)-measurable quantities (A2); \(\Delta C_t < 0\) is information about the trajectory and is not equivalent to a regime flip.

6. Flip Risk and Transition Pressure

Flip risk \(F_t \in \mathcal{F}\) is a function of proximity and motion in the score space:

\[ \phi \,:\, \mathcal{C} \,\times\, \mathbb{R}^k \,\times\, \mathbb{R}^k \,\times\, \mathcal{G} \;\longrightarrow\; [0,\, F^{\max}], \qquad F_t \;=\; \phi\!\big(C_t,\, \Delta Z_t,\, \Delta^2 Z_t,\, G_t\big), \qquad \Delta^2 F_t \;=\; F_t - 2F_{t-1} + F_{t-2} \]

The map \(\phi\) is monotone-non-increasing in \(C_t\) (proximity to the boundary raises flip risk) and increasing in \(\|\Delta Z_t\|\) (velocity in the score space raises flip risk). Three properties hold by construction:

  • Change dominates level. Static-level exceedance alone is not sufficient for elevated transition pressure (Diebold & Rudebusch, 1996).
  • Acceleration emphasis. \(\Delta^2 F_t\) can be informative even when \(F_t\) has not crossed a static threshold.
  • No silent stabilization. Short or incomplete histories are labeled through the observability axis of Section 2; they are never imputed to Stable.

7. Disagreement

Score disagreement is the range across the structural-score axes (the live implementation applies the max–min functional on a designated axis subset):

\[ D_t^{\,score} \;=\; \max_{1 \,\le\, i \,\le\, k}\, Z_{i,t} \;-\; \min_{1 \,\le\, i \,\le\, k}\, Z_{i,t} \;\in\; \mathbb{R}_{\ge 0} \]

\(D_t^{\,score}\) is a live object and is one of the families that contributes to admissibility of an abstention (Section 8).

Surface disagreement is the indicator that eligible classification surfaces disagree on the structural label:

\[ D_t^{\,surface} \;=\; \mathbf{1}\!\big\{\, \exists\, j, k:\; L_{j,t} \neq L_{k,t},\;\; E(D_{j,t}) = E(D_{k,t}) = 1 \,\big\} \]

\(D_t^{\,surface}\) is research-only; it is measured but not wired into the live admissible-action map. Any promotion to live status would require an explicit, declarative governance pass (Section 10).

8. Abstention as an Admissible Decision

The policy map is

\[ \pi_t \,:\, \Omega_t \;\longrightarrow\; \mathcal{U} \cup \{\varnothing\} \]

where \(\mathcal{U}\) is the set of admissible non-null exposure actions and \(\varnothing\) denotes no action — abstention. In the current implementation:

\[ \mathcal{U} \;=\; \{\mathrm{Allocate},\, \mathrm{Reduce}\}, \qquad \pi_t \,\in\, \mathcal{U} \cup \{\varnothing\} \]

The admissible decision set at time \(t\) is the gated subset

\[ u \,:\, \mathcal{S} \,\times\, \mathcal{T} \,\times\, \mathcal{C} \,\times\, \mathcal{F} \,\times\, \mathbb{R}_{\ge 0} \,\times\, \mathcal{G} \;\longrightarrow\; 2^{\,\mathcal{U} \cup \{\varnothing\}}, \qquad \mathcal{U}_t \;=\; u\!\big(S_t,\, T_t,\, C_t,\, F_t,\, D_t^{\,score},\, G_t\big), \qquad \pi_t \,\in\, \mathcal{U}_t \]

where \(u\) is the admissibility map and \(\pi_t\) is \(\mathcal{F}_t\)-measurable by A2. Gating reduces the action set; it does not select within it.

Abstention is not failure. It is a first-class output with reason codes, an episode lifecycle, and governance attribution. ATLAS manages exposure to uncertainty; it does not maximize return. This formulation follows the reject-option framework of Chow (1970) and its extension to selective classification in El-Yaniv & Wiener (2010).

An abstention episode is a maximal time interval over which \(\pi_t = \varnothing\), paired with a post-hoc outcome label. Formally:

\[ \mathcal{E}^{\,\mathrm{abst}} \;=\; \big\{\,(\,t_{\mathrm{enter}},\, t_{\mathrm{exit}},\, \omega\,) \,:\, \pi_t = \varnothing \;\forall\, t \in [t_{\mathrm{enter}},\, t_{\mathrm{exit}}),\;\; \omega \in \{\mathrm{JC},\, \mathrm{FC},\, \mathrm{IN}\}\,\big\} \]

where the outcome label \(\omega\) is assigned post-hoc at a pre-registered forward horizon:

  • \(\omega = \mathrm{JC}\) (Justified Caution) — forward drawdown of sufficient magnitude (abstaining avoided realized loss);
  • \(\omega = \mathrm{FC}\) (False Caution) — forward drawdown within tolerance (abstaining was unnecessary);
  • \(\omega = \mathrm{IN}\) (Inconclusive) — insufficient forward data or intermediate outcome.

Horizons and drawdown thresholds are declared in advance to prevent horizon-selection bias (Harvey, Liu & Zhu, 2016). \(\mathcal{E}^{\,\mathrm{abst}}\) is the input set to the LANTERN confusion matrix (Section 12).

9. Policy Separation

ATLAS enforces four disjoint layers. The boundaries are architectural, not stylistic; each is stated as a measurability or domain identity.

  • Measurement \(\neq\) policy. \(C_t,\, F_t,\, D_t^{\,score}\) are \(\mathcal{F}_t\)-measurable inputs to the admissibility map \(u\). They are not elements of \(\mathcal{U}_t\); knowing a measurement does not constitute taking an action.
  • Policy \(\neq\) execution. \(\pi_t \in \mathcal{U}_t\) is a posture. The execution map is a separately scoped function on \(\mathcal{F}_t\) and is gated by operator authorization (Section 11); a posture is not a trade.
  • Reporting \(\neq\) allocation authorization. A reported state object is \(\mathcal{F}_t\)-measurable; allocation authority requires \(\operatorname{Auth}(o, s, r) = 1\) (A5) and is not implied by the reportability of the underlying state.
  • Research \(\neq\) live governance. Shadow and research artifacts are \(\mathcal{F}_t\)-measurable but do not enter the domain of \(u\). Promotion to live governance requires passing the gates of Section 10.

10. Validation and Governance

Let \(\mathcal{V} = \{V_1, V_2, \ldots, V_n\}\) be the family of validators, each producing a closed-set verdict:

\[ V_j(D_i) \;\in\; \{\mathrm{PASS},\, \mathrm{FAIL},\, \mathrm{INSUFFICIENT}\} \]

Fail-closed semantics:

\[ \exists\, j \,:\; V_j(D_i) = \mathrm{FAIL} \quad\Longrightarrow\quad E(D_i) = 0 \]

The validator family covers, at minimum:

  • schema validation (column presence, type, closed-set membership);
  • key uniqueness;
  • date class consistency;
  • freshness (\(\ell_i(t)\) within tolerance);
  • stale-state propagation: if \(D_j\) is computed from \(D_i\), then \(q_i(t) \neq \mathrm{OK} \Rightarrow q_j(t) \neq \mathrm{OK}\) (downstream artifacts inherit upstream non-OK states; they do not mask them);
  • shadow / governed-track separation (no mutation of governed roots from shadow surfaces);
  • promotion gates (explicit, declarative, pre-registered);
  • operator authorization (Section 11).

A \(\mathrm{FAIL}\) verdict is non-recoverable: governance refuses to publish. \(\mathrm{INSUFFICIENT}\) expresses a well-defined computation against a sample too thin to commit a value — it is labeled, not silently coerced to Stable or to a default. Governed roots are never written from shadow tracks. Hypotheses that fail empirical validation are recorded and disabled (Popper, 1959).

11. Multitenancy and Operator Scope

Let \(o \in \mathcal{O}\) denote an operator and \(s \in \mathcal{S}_o\) a sleeve in that operator’s scope. Authorization is a closed-set predicate over \((o, s, r)\) where \(r\) is the requested resource:

\[ \operatorname{Auth}(o,\, s,\, r) \;\in\; \{0,\, 1\} \]

A request is valid only if

\[ o \neq \varnothing \;\;\land\;\; s \in \mathcal{S}_o \;\;\land\;\; \operatorname{Auth}(o,\, s,\, r) = 1 \]

Missing operator context is fail-closed: a surface that requires \((o, s)\) to be safe refuses to render rather than render against a default. Let \(\mathrm{scope}(D)\) return the \((o, s)\) tuple to which an artifact is scoped, with \((o, \varnothing)\) marking org-wide artifacts. The per-operator-sleeve filtration is

\[ \mathcal{F}_t^{(o,\,s)} \;=\; \sigma\!\Big(\,\big\{\, D_{i,\,t}(d) \,:\, E(D_{i,\,t}) = 1,\;\; \mathrm{scope}(D_i) \in \{(o, s),\, (o, \varnothing)\},\;\; d \le t\,\big\}\,\Big) \]

Cross-sleeve leakage is structurally prohibited: any value rendered for \((o, s)\) is \(\mathcal{F}_t^{(o,s)}\)-measurable, and \(\mathcal{F}_t^{(o,s)} \cap \mathcal{F}_t^{(o,s')}\) for \(s \neq s'\) contains only org-wide \((o, \varnothing)\) state. Reports, exports, overrides, governed artifacts, and promotion gates are all scoped to \((o, s)\). The audit trail records \(\mathrm{scope}(\cdot)\) for any action taken, so post-hoc review can reconstruct what was observable when a decision was made.

12. Measurement Programs

The programs below are measurement and evaluation tracks, each with an explicit status tag. None of them are allocation engines on their own; promotion to live policy requires the gates of Section 10.

HEDGEHOG   STATUS: LIVE. A forensic-measurement program for the regime-and-tactical stack. Its scope is the tuple of measurement axes

\[ \mathcal{H} \;=\; \big(\mathrm{cov},\, \mathrm{lat},\, \mathrm{per},\, \mathrm{cal},\, \mathrm{lk}\big) \]

Each axis admits a formal definition over a discrete window \(W = [t_0, t_1] \cap \mathbb{Z}_{\ge 0}\) and a scope \(R\) (a subset of artifacts, regimes, or sleeves):

\[ \begin{aligned} \mathrm{cov}_R(W) \;&=\; \frac{1}{|W|}\,\Big|\,\big\{\,t \in W \,:\, R \subseteq \{\,i \,:\, E(D_{i,t}) = 1\,\}\,\big\}\,\Big| \\[6pt] \mathrm{lat}_i(W) \;&=\; \mathrm{median}\,\big\{\,\ell_i(t) \,:\, t \in W\,\big\} \\[6pt] \mathrm{per}(s) \;&=\; \mathbb{E}\!\big[\,\tau_s\,\big], \qquad \tau_s \;=\; \min\!\big\{\,h \ge 0 \,:\, S_{t+h} \ne s \,\big|\, S_t = s\,\big\} \\[6pt] \mathrm{cal}(W) \;&=\; \sum_{k=1}^{K}\,\frac{|B_k|}{|W|}\,\Big|\,\overline{\hat{p}}^{\,(B_k)} - \overline{y}^{\,(B_k)}\,\Big| \\[6pt] \mathrm{lk}(W) \;&=\; I\!\big(\,S_t \,;\, T_t \,\big|\, Z_t\,\big) \;\;\text{over}\;\; t \in W \end{aligned} \]

Reading the axes:

  • Coverage \(\mathrm{cov}_R(W)\): fraction of decision times at which every artifact in scope \(R\) was eligible (Section 2).
  • Latency \(\mathrm{lat}_i(W)\): median artifact lag \(\ell_i(t)\) (Section 2) over the window; tail-percentile variants are reported alongside the median.
  • Persistence \(\mathrm{per}(s)\): expected dwell time in structural state \(s\); the architectural prior \(\mathbb{P}(S_{t+h} = S_t) \gg \mathbb{P}(T_{t+h} = T_t)\) (Section 3) is checked against \(\mathrm{per}(s)\).
  • Calibration \(\mathrm{cal}(W)\): expected calibration error over confidence bins \(\{B_k\}\) partitioning the unit interval, with \(\overline{\hat{p}}^{(B_k)}\) the bin-mean predicted probability and \(\overline{y}^{(B_k)}\) the realized rate.
  • Leakage \(\mathrm{lk}(W)\): conditional dependence between structural and tactical states given the observable score vector; \(I(\,\cdot\,;\,\cdot\mid\cdot\,)\) is conditional mutual information (or an equivalent conditional-dependence functional). The architectural invariant is \(\mathrm{lk}(W) \approx 0\); persistent positive deviations are escalated for review.

HEDGEHOG is a measurement program, not an allocation surface. None of \(\mathrm{cov}\), \(\mathrm{lat}\), \(\mathrm{per}\), \(\mathrm{cal}\), \(\mathrm{lk}\) enters \(\mathcal{U}_t\). Instrumentation depth along each axis is itself a HEDGEHOG-reported metric, not a uniform claim of completeness.

SENTINEL   STATUS: RESEARCH. Transition-forecasting evaluation. Let \(\hat{p}^{(M)}_{ij}(t; h)\) denote model \(M\)'s estimate of \(\mathbb{P}(S_{t+h} = j \mid S_t = i)\). For a horizon \(h\), a scoring rule \(\ell\), and an out-of-sample index set \(\mathcal{I}_h\):

\[ \mathcal{L}^{(M)}(h) \;=\; \frac{1}{|\mathcal{I}_h|} \sum_{t \,\in\, \mathcal{I}_h} \ell\!\big(\hat{p}^{(M)}_{\,\cdot\,j}(t; h),\, \mathbf{1}\{S_{t+h} = j\}\big), \qquad \Delta\mathcal{L}(h) \;=\; \mathcal{L}^{(B)}(h) - \mathcal{L}^{(C)}(h) \]

SENTINEL reports \(\Delta\mathcal{L}(h)\) over a held-out window and across horizons \(h\), comparing a baseline \(B\) to a candidate \(C\). There is no map from \(\Delta\mathcal{L}\) into \(\mathcal{U}_t\): SENTINEL is measurement of forecastability, not policy.

LANTERN   STATUS: SHADOW. Caution-policy calibration. Let \(\pi_t^{\star}\) denote a post-hoc reference action evaluated against forward outcome at a pre-registered horizon (see Section 8). LANTERN computes the policy-state confusion matrix over the realized policy \(\pi_t\) and the reference \(\pi_t^{\star}\):

\[ \Lambda \;=\; \big(\,M_{\pi,\,\pi^{\star}}\,\big)_{\pi,\,\pi^{\star} \,\in\, \mathcal{U} \cup \{\varnothing\}}, \qquad M_{\pi,\,\pi^{\star}} \;=\; \big|\,\{\,t \,:\, \pi_t = \pi,\;\; \pi_t^{\star} = \pi^{\star}\,\}\,\big| \]

\(\Lambda\) is reviewed by operators in a shadow learning surface. LANTERN does not write into \(\Pi\); there is no \(\Lambda\)-derived map into \(\mathcal{U}_t\).

TICM   STATUS: LIVE labeling. Stress-event window labeling. TICM defines a family of event windows and a corresponding indicator:

\[ \mathcal{E}^{\,\mathrm{TICM}} \;=\; \{\, W_1,\, W_2,\, \ldots\,\}, \qquad W_e \;=\; [\,t_e^{\,\mathrm{start}},\, t_e^{\,\mathrm{end}}\,], \qquad \tau_t^{\,\mathrm{TICM}} \;=\; \mathbf{1}\!\big\{\, t \,\in\, \textstyle\bigcup_e W_e \,\big\} \]

\(\tau_t^{\,\mathrm{TICM}}\) participates as a conditioning variable in the evaluation programs above. TICM labels never enter \(\mathcal{U}_t\) directly and carry no policy authority of their own.

WS7   STATUS: RESEARCH. Surface-disagreement track. Building on \(D_t^{\,surface}\) (Section 7), WS7 reports the windowed disagreement rate

\[ \rho^{\,\mathrm{WS7}}_{[t_0,\, t_1]} \;=\; \frac{1}{t_1 - t_0 + 1} \sum_{t \,=\, t_0}^{t_1} D_t^{\,surface} \]

and stratifications of it by structural regime \(S_t\) and by TICM label \(\tau_t^{\,\mathrm{TICM}}\). WS7 is measured but not wired into \(\mathcal{U}_t\); there is no \(\rho^{\,\mathrm{WS7}}\)-derived gate on \(\pi_t\).

13. Optionality / Protection Measurement

A protection bundle at decision time \(t\) is a finite set of contracts

\[ \mathcal{P}_t \;=\; \big\{\,(\,k_j,\, n_j,\, c_j\,) \,:\, j = 1,\, \ldots,\, J\,\big\}, \qquad k_1 < k_2 < \cdots < k_J, \qquad n_j \,\in\, \mathbb{Z}_{\ge 0} \]

with strike grid \(\{k_j\}\), contract counts \(\{n_j\}\), and per-contract proxy premia \(\{c_j\}\). The protection-cost proxy is

\[ P_t^{\,\mathrm{proxy}} \;=\; \sum_{j=1}^{J} n_j \cdot c_j^{\,(t_0)} \qquad \text{labeled}\;\; \texttt{ESTIMATE\_PROXY}, \;\; \text{row-level qualifier required} \]

where \(c_j^{(t_0)}\) is the contract-proxy premium taken at a snapshot date \(t_0\) (\texttt{STATIC\_PROXY\_AT\_T0}) — not the live mid-market price at \(t\). The budget constraint is

\[ P_t^{\,\mathrm{proxy}} \;\le\; B_t, \qquad B_t \,\text{ is }\, \mathcal{F}_t\text{-measurable} \]

The Slice F successor would replace each \(c_j^{(t_0)}\) by a live mid-market \(c_j(t)\) drawn from an option-chain pricing surface; this remains DEFERRED. Until promotion, \(P_t^{\,\mathrm{proxy}}\) carries no allocation, abstention, or gross-reduction authority and does not equal the realizable cost of acquiring \(\mathcal{P}_t\) at \(t\). It is a reporting estimate, labeled as such at the row level.

14. Estimation, Calibration, and Uncertainty

Only methods that are implemented or explicitly evaluated against ATLAS data are described here. ATLAS does not claim methods it does not use.

Structural-regime estimation is in the regime-switching tradition (Hamilton, 1989) with a finite latent state and a transition matrix \(P\) (Section 3). Parameters \(\Theta_S\) and \(\Theta_T\) are estimated on a calibration window declared in advance and held out from out-of-sample evaluation:

\[ W_{\mathrm{cal}} \,\subset\, \mathbb{Z}, \qquad W_{\mathrm{oos}} \,\subset\, \mathbb{Z}, \qquad W_{\mathrm{cal}} \,\cap\, W_{\mathrm{oos}} = \varnothing \]

For a generic parameter \(\theta \in \Theta\):

\[ \hat{\theta} \;=\; \arg\min_{\theta \,\in\, \Theta}\; \mathcal{L}\!\big(\,X_{\,t \in W_{\mathrm{cal}}}\,;\, \theta\,\big) \]

Sample-size guardrail. Estimators carry an explicit minimum-sample requirement \(n_{\min}(\theta)\); below threshold, the estimator returns a labeled non-value rather than committing one:

\[ |W_{\mathrm{cal}}| \,<\, n_{\min}(\theta) \quad\Longrightarrow\quad \hat{\theta} \;=\; \mathrm{INSUFFICIENT} \]

The following properties are encoded in the formal objects above and in Sections 2–8:

  • \(W_{\mathrm{cal}} \cap W_{\mathrm{oos}} = \varnothing\): calibration and out-of-sample windows are disjoint, declared before evaluation begins.
  • \(|W_{\mathrm{cal}}| < n_{\min}(\theta) \Rightarrow \hat{\theta} = \mathrm{INSUFFICIENT}\): the sample-size guardrail commits no value below threshold.
  • Forward evaluation horizons \(\{h_1, \ldots, h_K\} \subset \mathbb{Z}_{>0}\) are declared before \(W_{\mathrm{oos}}\) is entered, and outcomes for \(\mathcal{E}^{\,\mathrm{abst}}\) are aggregated across this fixed set (Harvey, Liu & Zhu, 2016; Tetlock & Gardner, 2015).
  • Composite uncertainty is the vector \((C_t,\, F_t,\, D_t^{\,score})\) feeding the admissibility map \(u\); it is not collapsed into a single continuous probability, since such a collapse would itself require a calibration model subject to the same instability (Taleb, 2007). Admissibility \(u(\cdot) \in 2^{\,\mathcal{U} \cup \{\varnothing\}}\) is a closed-set output.

Parametric confidence intervals, bootstrap-based interval estimation, and spline-based smoothing are not claimed as components of the live estimation stack. Parameter uncertainty is real and is not collapsed into false precision.

15. Public Mathematical Glossary

Every cross-section ATLAS symbol introduced in Sections 1–14 and 16 appears below with its domain, interpretation, implementation status, and a public-safety note. Standing assumptions A1–A5 are stated in Section 1.1. Standard set-theoretic and probability notation is not duplicated. Program-local symbols defined inline within a single subsection — the abstention-episode set \(\mathcal{E}^{\,\mathrm{abst}}\) and outcome labels \(\{\mathrm{JC}, \mathrm{FC}, \mathrm{IN}\}\) (Section 8); the scope predicate \(\mathrm{scope}(\cdot)\) and per-operator-sleeve filtration \(\mathcal{F}_t^{(o,s)}\) (Section 11); the structural decision boundary \(\Gamma\) (Section 5); the HEDGEHOG axes \(\mathrm{cov},\, \mathrm{lat},\, \mathrm{per},\, \mathrm{cal},\, \mathrm{lk}\) and supporting \(W,\, R,\, B_k,\, \tau_s\); the SENTINEL objects \(\hat{p}^{(M)},\, \mathcal{L}^{(M)},\, \Delta\mathcal{L},\, \mathcal{I}_h\); the LANTERN objects \(\pi_t^{\star},\, \Lambda,\, M_{\pi,\,\pi^{\star}}\); the TICM objects \(\mathcal{E}^{\,\mathrm{TICM}},\, W_e,\, \tau_t^{\,\mathrm{TICM}}\); the WS7 statistic \(\rho^{\,\mathrm{WS7}}\); the optionality objects \(\mathcal{P}_t,\, k_j,\, n_j,\, c_j,\, B_t\); the calibration objects \(W_{\mathrm{cal}},\, W_{\mathrm{oos}},\, n_{\min}\); and the admissibility map \(u\) — are not duplicated here. Implementation status is one of LIVE, SHADOW, RESEARCH, or DEFERRED.

Symbol Domain Interpretation Status Public-safe note
\(t\)\(\mathbb{Z}_{\ge 0}\)decision time indexLIVE
\(d\)calendar datesobservation dateLIVE
\(X_t\)\(\mathcal{X} \subseteq \mathbb{R}^p\)observable state vectorLIVE
\(D_i\)\(\mathcal{D}\)governed artifact \(i\)LIVEschema / keys / dates validated
\(G_t\)\(\mathcal{G}\)artifact-admissibility stateLIVEfail-closed
\(\mathcal{F}_t\)\(\sigma\)-algebranatural artifact filtration at \(t\)LIVEdistinct from flip risk \(F_t\) (calligraphic vs italic)
\(Z_t\)\(\mathbb{R}^k\)structural-score vectorLIVEgrowth / inflation / risk / liquidity axes
\(S_t\)finite \(\mathcal{S}\)structural regimeLIVEslow, persistent
\(T_t\)\(\{\text{Stable},\, \text{Transitional},\, \text{Unstable}\}\)tactical instability stateLIVEfast, fail-closed
\(P\)\([0,\,1]^{|\mathcal{S}|\times|\mathcal{S}|}\), row-stochasticstructural transition matrixLIVEdiagonal = self-persistence; member of \(\Theta_S\)
\(\Theta_S\)parameter space of \(f_S\)governed structural parametersLIVEvalues undisclosed; calibrated on declared window
\(\Theta_T\)parameter space of \(f_T\)governed tactical parametersLIVEvalues undisclosed
\(H_t\)\(\mathbb{Z}_{\ge 0}\)transitional severityLIVEtactical scalar; thresholds undisclosed
\(N_t\)\(\{0,\, 1\}\)NA-driven indicatorLIVEroutes to Transitional when set
\(K_t\)\(\mathbb{Z}_{\ge 0}\)trigger countLIVEnumber of active triggers at \(t\)
\(C_t\)\(\mathbb{R}_{\ge 0}\)confidence (margin form)LIVEgeometric form is SHADOW
\(F_t\)\(\mathbb{R}\)flip-risk / transition pressureLIVEacceleration-aware
\(\Delta\)operatorfirst differenceLIVE
\(\Delta^2\)operatorsecond differenceLIVE
\(D_t^{\,score}\)\(\mathbb{R}_{\ge 0}\)score-axis dispersionLIVEcontributes to abstention admissibility
\(D_t^{\,surface}\)\(\{0,\, 1\}\)surface-label disagreementRESEARCHnot policy-wired (WS7)
\(\pi_t\)\(\mathcal{U} \cup \{\varnothing\}\)policy / exposure postureLIVEno execution authority
\(\varnothing\)distinguished element of \(\Pi\)abstain (no action)LIVEfirst-class output
\(V_j\)\(\mathcal{D} \to \{\mathrm{PASS},\, \mathrm{FAIL},\, \mathrm{INSUFFICIENT}\}\)validatorLIVEfail-closed on FAIL
\(E(D_i)\)\(\{0,\, 1\}\)artifact eligibilityLIVEcomposite of schema / keys / dates / state
\(o\)\(\mathcal{O}\)operatorLIVEmissing \(\Rightarrow\) fail-closed
\(s\)\(\mathcal{S}_o\)sleeve in operator scopeLIVEno cross-sleeve leakage
\(\operatorname{Auth}\)\((o, s, r) \to \{0,\, 1\}\)authorization predicateLIVEclosed-set; logged

Programs (Section 12) carry their own tags: HEDGEHOG LIVE, TICM LIVE labeling, LANTERN SHADOW, SENTINEL RESEARCH, WS7 RESEARCH. The optionality proxy \(P_t^{\,\mathrm{proxy}}\) (Section 13) is ESTIMATE_PROXY; real option-chain pricing is DEFERRED.

16. Non-Claims

Three statements, made explicitly to prevent inferential drift.

ATLAS does not assert

\[ \mathbb{E}\!\left[\,r_{t+1} \,\middle|\, \mathcal{F}_t\,\right] \;>\; 0 \]

as a universal trading claim.

ATLAS does not define

\[ a_t \;=\; \arg\max_a\; \mathbb{E}\!\left[\,U(W_{t+1})\,\right] \]

as an unconstrained return-maximization problem.

ATLAS does define

\[ a_t \,\in\, \mathcal{A}_t\!\big(S_t,\, T_t,\, G_t\big), \qquad \mathcal{A}_t \;\text{governed by}\; \mathcal{V}\;\text{and}\;\operatorname{Auth}(o,\, s,\, r) = 1 \]

The objective ATLAS is governing is exposure to uncertainty under regime instability, subject to validation \(\mathcal{V}\), operator scope \((o, s)\), and the layer separation of Section 9. It is not portfolio-return maximization under regime stability. The two problems are complementary, not interchangeable.

References

Ang, A. & Timmermann, A. (2012). Regime changes and financial markets. Annual Review of Financial Economics, 4, 313–337.

Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.

Chow, C. K. (1970). On optimum recognition error and reject tradeoff. IEEE Transactions on Information Theory, 16(1), 41–46.

Diebold, F. X. & Rudebusch, G. D. (1996). Measuring business cycles: A modern perspective. Review of Economics and Statistics, 78(1), 67–77.

El-Yaniv, R. & Wiener, Y. (2010). On the foundations of noise-free selective classification. Journal of Machine Learning Research, 11, 1605–1641.

Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357–384.

Harvey, C. R., Liu, Y. & Zhu, H. (2016). … and the cross-section of expected returns. Review of Financial Studies, 29(1), 5–68.

Popper, K. R. (1959). The Logic of Scientific Discovery. Hutchinson.

Taleb, N. N. (2007). The Black Swan: The Impact of the Highly Improbable. Random House.

Tetlock, P. E. & Gardner, D. (2015). Superforecasting: The Art and Science of Prediction. Crown.

Contact

Ask about ATLAS


0 / 2000