Research Framework

How A Forecast Gets Built, Not Guessed.

Eaglics forecasts are not opinions about where a pair might go. They are the output of a defined research pipeline: historical price data, engineered market features, a five-model ensemble, dynamic weighting, and a confidence score , all computed before the session opens, and all measured against what actually happens afterward.

Data
Features
Ensemble
Weighting
Confidence
Forecast
0Independent Models
0Forecasted Components
0Continuous Retraining
// 01 The Forecasting Pipeline

Six Stages, Completed Before The Candle Opens.

Every daily forecast passes through the same defined sequence. Nothing is manually adjusted between stages , the pipeline runs the same way for every pair, every session.

01

Historical Price Data

Multi-year OHLC price history is pulled per pair as the raw input layer.

02

Feature Engineering

Raw prices are converted into statistical features the models can actually learn from.

03

Five-Model Ensemble

LSTM, GRU, Transformer, XGBoost, and Ridge each independently forecast the session.

04

Dynamic Weighting

Each model's output is blended, weighted per component by recent reliability.

05

Confidence Scoring

A blended confidence score and market regime classification is attached to the forecast.

06

Forecast Output

Forecast High, Low, Close, and Range are published before the session opens.

// 02 What The Models Actually See

Price Alone Is Not A Feature.

Raw candles are noisy. Before any model touches a session, price history is converted into a set of statistical features that describe the underlying condition of the market , direction, volatility, and behavioral regime.

Regression Slope

Measures the underlying directional bias of price over the recent window , is the pair trending or flat.

Direction

Bollinger Band Expansion

Tracks how far volatility bands are stretching, signaling whether a range is compressing or breaking out.

Volatility

Average True Range

The typical size of recent price movement, used to calibrate how wide a forecasted range should be.

Volatility

Dispersion

Quantifies how scattered recent price outcomes are relative to the mean , a proxy for market noise.

Noise

Hurst Exponent

Distinguishes trending from mean-reverting behavior , a value above 0.5 favors trend, below favors reversal.

Behavior

Regime Classification

Sessions are tagged by prevailing market condition, so the ensemble adapts to the environment it is forecasting in.

Context
// 03 The Five-Model Ensemble

No Single Model Is Trusted Alone.

Five architecturally different models are trained independently on the same feature set. Each has different strengths , some read sequence and memory well, others read structured statistical relationships better. None of them vote equally by default.

LSTMSequential memory network
18.8%
GRULightweight recurrent network
16.2%
TransformerAttention-based sequence model
20.0%
XGBoostGradient-boosted decision trees
28.5%
RidgeRegularized linear regression
16.5%

Average contribution across a recent sample window, shown for illustration , actual weighting is recalculated per forecast, not fixed.

Weighting Is Per-Output, Not Global

A model that forecasts the high well is not automatically trusted for the low, the close, or the range. Each of the six forecasted components gets its own independently calculated weighting across the ensemble.

High
Low
Close
Range
Slope
Expansion
// 04 Confidence & Market Regime

Every Forecast Carries A Confidence Score.

Model agreement is not constant , some sessions produce tightly aligned outputs across the ensemble, others do not. That agreement is captured as a confidence score and paired with a regime read, so a forecast never arrives without context on how reliable it is likely to be.

Model Agreement, Sample SessionReal Logged Values
Confidence: Expansion Component20 Prior Sessions →

Confidence Score

A single blended figure derived from how closely the five models agree across every forecasted component.

Hurst Exponent Read

Classifies the session as trend-persistent or mean-reverting, informing how the range forecast is shaped.

Volatility Regime

Sessions are tagged by prevailing volatility condition so forecasts adapt to calm versus expansive markets.

Never A Fixed Number

Confidence shifts session to session based on real model agreement , it is never a flat, marketed accuracy figure.

// 05 Historical Validation

Every Forecast Is Graded After The Fact.

Once a session closes, the forecast is compared against what actually happened. Below is a sample of logged forecast-to-actual comparisons from a recent validation window , not curated for best results, shown in pips of deviation.

4.7 pipsAvg. High Deviation
6.1 pipsAvg. Low Deviation
0.62Avg. Confidence Score
PairDateForecast H / LActual H / LDeviation

Sample drawn from a recent three-month validation window across two pairs. Deviation figures are illustrative of the tracking process, not a forward-looking accuracy guarantee.

// 06 Continuous Retraining

The Loop Never Stops.

A forecast is not the end of the research process , it is one data point feeding the next model update.

Forecast Published
Session Closes
Compared To Actual
Error Logged
Models Retrained
Weights Recalculated
Forecast Published
Session Closes
Compared To Actual
Error Logged
Models Retrained
Weights Recalculated
// 07 Scope Of The Research

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

What It Does

Produces a structured, probabilistic estimate of a session's likely high, low, close, and range, grounded in historical model performance and updated continuously as new sessions complete.

What It Doesn't

It does not predict the future with certainty, does not issue trade instructions, and does not guarantee that any given session will land inside the forecasted range.

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.

Deep Dive
The Pipeline in Detail
Stage-by-stage technical breakdown of how Eaglics models the daily range.
Statistical Argument
Why Range Beats Direction
Why daily high/low is more forecastable than the direction of price within those boundaries.
Get Access
View Pricing Plans
Start with one pair at $200/mo. Upgrade anytime from the dashboard.