Research Framework

Systematic Forecasting. Not Guesswork.

Eaglics is built as a quantitative research process, not a trading opinion. Raw price history is transformed into an orthogonalized factor library, conditioned on the prevailing volatility regime, passed through a multi model ensemble, checked at every stage for point in time data integrity, and graded against realized outcomes once each session closes. Nothing in that process is discretionary.

108Orthogonalized Factors
5Model Ensemble
9Currency Pairs Covered
// 01 Data Infrastructure

Point In Time Integrity, Enforced Structurally.

The research process is built on a point in time data discipline, the same standard institutional quant desks hold their own pipelines to. Every observation is bound to the information that was genuinely available at that moment, survivorship and revision bias are controlled for, and cross instrument scaling is normalized so that pairs with different tick and pip conventions are directly comparable inside the same factor space.

01

Multi Horizon Ingestion

Price history is ingested across multiple sampling frequencies per instrument.

02

Point In Time Enforcement

A structural boundary prevents any observation beyond the evaluation point from entering the factor set.

03

Cross Instrument Normalization

Price scale conventions are reconciled so every pair sits on a comparable footing.

04

Macro Conditioning

Each instrument is conditioned against a curated set of correlated macro drivers.

05

Factor Construction

Verified, boundary safe data flows into the factor construction layer.

No currency pair trades in isolation. Each instrument carries systematic exposure to broader macro factors, rate differentials, risk sentiment, and cross asset flow, and that exposure is incorporated as conditioning context rather than treated as noise.

Coverage: EURUSD · GBPUSD · USDCHF · GBPCHF · AUDUSD · GBPJPY · EURGBP (Free)

// 02 Factor Construction

An Orthogonalized Multi Factor Library.

Price alone carries almost no usable information for a learning system. A broad candidate factor set is constructed across seven domains of market behavior, statistical dispersion, directional persistence, microstructure, liquidity geometry, session conditioning, denoised price structure, and long memory regime. Every candidate factor is subject to strict ex ante lag enforcement, so a factor evaluated at a given point can only reflect information that was already realized. Collinear factors are then removed through a systematic orthogonalization process, leaving a compact library where each surviving factor carries distinct, non redundant information.

Domain · Dispersion

Realized Volatility & Statistical Moments

Multi window realized volatility, skewness, and kurtosis, capturing how asymmetric and fat tailed recent return behavior has been.

Domain · Persistence

Directional Persistence Factors

Streak based and slope based measures of whether the instrument is presently trending or range bound.

Domain · Microstructure

Order Flow & Absorption

Volume weighted pressure measures, a market efficiency ratio, and absorption intensity at price extremes.

Domain · Liquidity Geometry

Auction & Value Area Structure

Where liquidity actually concentrated over a trailing window, and distance from those structural levels.

Domain · Session Conditioning

Cross Session Interaction

Conditional range and breakout probabilities across overlapping global trading sessions.

Domain · Denoised Structure

Causal Spectral Filtering

A strictly trailing filter separates the underlying price path from short term noise, with zero forward information leakage.

Domain · Long Memory

Fractal Memory Regime

A long memory statistic classifies the instrument as trend persistent or mean reverting through time.

↑ Systematic correlation pruning reduces the candidate set to an orthogonalized factor library

// 03 Regime Conditioning

Dispersion Is Not Constant, So The Model Should Not Treat It That Way.

Volatility clusters through time, calm periods tend to persist, and turbulent periods tend to persist. A regime classifier ranks current dispersion against its own trailing distribution, and a parallel conditional variance model provides an independent forward looking read. Together they recalibrate the width and confidence of every forecast, so a quiet session and a post event, high dispersion session are never scored against the same yardstick.

LOW VOLATILITY
Low percentile dispersion
Compressed conditions
Interval tightened
NEUTRAL
Mid percentile dispersion
Standard conditions
Baseline interval
HIGH VOLATILITY
Elevated percentile dispersion
Widening conditions
Interval widened
EVENT DAY
Tail percentile dispersion
Shock conditions
Interval maximally widened

The regime read itself is subject to the same ex ante lag enforcement as every other factor, so today's forecast is only ever conditioned on a regime that was already confirmed as of the prior close.

// 04 Model Ensembling

A Diversified Ensemble, Not A Single Point Estimate.

No single estimator is trusted in isolation. Five architecturally distinct model families are trained independently on the same orthogonalized factor library, then combined across six forecast targets, expected close, high and low boundaries, expected range, trend slope, and dispersion expansion. Each family contributes a different statistical lens on the same data, and a regime aware meta learner determines how much weight each one receives depending on the prevailing memory regime.

Tree EnsembleCaptures nonlinear feature interactions, weighted up in persistent regimes
Boosting
Regularized LinearA robust linear baseline, weighted up in mean reverting regimes
Averaging
Recurrent Sequence ModelReads a trailing multi period sequence window for temporal structure
Sequence
Attention Sequence ModelA second, independent read of the same sequence window
Sequence
Latent Factor AutoencoderCompresses the factor library into a small latent space to surface nonlinear cycles
Latent Alpha
Regime Conditioned Weighting, Not A Static Blend

The long memory regime read determines how much say each model family gets at any point in time. Tree based and sequence based estimators are weighted up in persistent, trending conditions, while the linear baseline is weighted up in mean reverting conditions. The latent factor model contributes a continuous nonlinear check across every regime. None of the five ever forecasts alone.

// 05 Leakage Control

The Single Greatest Risk In Quantitative Research Is Leakage.

A forecasting process that performs well in backtest and fails in production has almost always leaked future information into training somewhere. This process is built around three structural guardrails designed specifically to close that gap.

Closed
Realized history
Lagged
Factor source, ex ante enforced
Boundary
Target
Forecast horizon, unseen by the model
Future
Unrealized

Purged Walk Forward Validation

Evaluation proceeds strictly in chronological order with a purge and embargo applied around every split, so no observation adjacent to a test period can bleed information across the boundary.

Structural Ex Ante Lag Enforcement

Every factor is bound to information that was already realized as of the prior close. The model is structurally prevented from ever touching a still forming observation.

Outcome Leakage Exclusion

Any feature that could encode a realized result or downstream outcome is excluded at the earliest stage of construction, so the process can never condition on its own prior performance.

// 06 Recursive Calibration

A Closed Loop Research Process, Not A Static Model.

A forecast is not graded once and forgotten. Once a session closes, a recursive calibration process runs automatically ahead of the next forecast cycle.

01

Error Minimization

Realized outcomes are compared against prior forecasts, and ensemble weights update to minimize forecast error.

02

Rolling Bias Correction

A rolling calibration window checks for systematic bias in either direction, and any persistent offset is corrected out of future predictions.

03

Directional Drift Guard

Directional accuracy is tracked continuously, and a correction mechanism engages automatically if performance degrades beyond an internally defined threshold.

Forecast Published
Session Closes
Compared To Actual
Bias Measured
Weights Updated
Forecast Published
Session Closes
Compared To Actual
Bias Measured
Weights Updated
// 07 Microstructure Timing

The Forecast Sets Direction. Microstructure Sets Timing.

Once a forecast horizon is established, a separate microstructure layer evaluates order flow imbalance to condition the timing of implementation against that horizon. Rather than a fixed trigger, an adaptive threshold is derived statistically from recent order flow behavior, so the bar for confirmation relaxes in quiet conditions and rises in expanding, high dispersion conditions to guard against premature signals.

01

Forecast Horizon

The session level forecast sets the directional context.

02

Order Flow Read

Live order flow is evaluated for directional pressure in real time.

03

Rolling Statistics

A rolling distribution of pressure readings is maintained.

04

Adaptive Threshold

A statistically derived, regime sensitive confirmation threshold is applied.

05

Implementation

Timing is confirmed only once the adaptive threshold is cleared.

// 08 Validation Framework

Accuracy Is Measured Relative To The Market, Not In A Vacuum.

A raw pip error means little on its own, since it is tight for one instrument and loose for another. Forecast error is instead normalized against realized volatility, producing a standardized accuracy read that is directly comparable across every instrument in the coverage set.

Volatility Normalized Accuracy

Forecast error is expressed as a proportion of realized volatility rather than as an absolute figure. An error on the scale of typical dispersion for that instrument scores low, while an error well inside typical dispersion scores high, placing every pair on one standardized scale regardless of its native volatility profile.

Directional Accuracy

Tracked independently, this measures whether the session closed in the direction the forecast implied, and feeds directly into the drift guard described in Section 06.

A rolling out of sample verification database of paired forecasts and realized outcomes is maintained continuously, and it is what drives the recursive weight tuning process.

// 09 Instrument Coverage

Seven Pairs. Independent Weights Each.

Eaglics runs the full pipeline, forecasting and execution, across seven major and cross currency pairs. Each pair keeps its own trained weights, its own feature whitelist, and its own validation history, rather than sharing a single generic model across all of them.

CategoryInstruments
FX MajorsEURUSD · GBPUSD · USDCHF · AUDUSD
FX CrossesEURGBP · GBPCHF · GBPJPY
// Scope Of The Research

What This Framework Does, And Doesn't, Claim.

What It Does

Produces a structured, volatility conditioned forecast of a session's likely high, low, close, and range across ten pairs, built on leakage controlled historical data and recalibrated after every closed session.

What It Doesn't

It does not predict the future with certainty, does not issue trade instructions, and does not guarantee any session will land inside its forecasted range. Forecasts are research prices, not signals.

Research Framework

The Pipeline Runs Every Session. See What It Produces.

Explore the live product to see the daily output of this exact research process.