Intratio
Quantitative Research
Skip to main content
AI Market Summary
Loading market intelligence...
Quantitative Equity Research

Systematic Alpha Generation Through Machine Intelligence

Daily machine-learning forecasts on every US-listed equity over two horizons, portfolio construction under your mandate's constraints, and a validation record computed on data the model never saw.

Coverage
4,000+
US-listed equities
Horizons
1M · 3M
Forecasts
Frequency
Daily
Post-market close
History
10+ yrs
Fundamentals
How It Works

From the Close to a Portfolio You Can Trade

The film in five chapters. Each chapter is a part of the platform you can open today; select a timestamp to watch it.

  1. 01Coverage

    The whole US market, read every evening

    4,000+ US-listed equities. Cleaned, normalised statements over 10+ years, market data and corporate events, refreshed after every close.

    Market map →
  2. 02Signals

    Every stock ranked, on two horizons

    Directional conviction on 1-month and 3-month forecasts, published every trading day after the close.

  3. 03Construction

    From signals to a portfolio

    Mean-variance optimization under your risk target, sector limits, position sizing, turnover, factor exposure and trading costs.

    Optimizer →
  4. 04Validation

    Evidence, not promises

    Walk-forward and embargoed, on a factor-neutral long/short book net of realised trading costs.

  5. 05Access

    Wherever you work

    Web platform, REST API, and an MCP server that plugs Intratio signals and the optimizer into AI assistants.

    API docs →

Also included: factor-exposure, correlation, drawdown and Value-at-Risk analytics on every portfolio, and the normalised fundamental dataset behind each forecast.

Research Process

A Disciplined Approach to Signal Discovery

Our research pipeline is built on the same principles that govern institutional quantitative funds: hypothesis-driven feature engineering, strict walk-forward validation, and continuous model monitoring.

01
Data Ingestion & Normalization

Daily automated collection and cleaning of financial statements, market data, corporate events, and macroeconomic indicators across the full US equity universe.

02
Feature Engineering

A proprietary feature set drawn from several independent data families. Every candidate is hypothesis-driven and admitted only on evidence of out-of-sample contribution; names and definitions are not disclosed.

03
Model Training & Validation

Ensemble machine-learning models trained on the factor-neutral part of returns, with purged, embargoed, regime-aware cross-validation and a strictly posterior test window that is opened once, after every modelling choice is frozen.

04
Signal Delivery & Monitoring

Daily post-market generation of forecasts with continuous IC tracking, regime detection, and automated model degradation alerts.

Market Map

The Whole Market, Lit by Today's Signals

Every covered company, sized by market capitalisation and grouped by sector. Zoom from the whole market down to a single forecast.

Explore the map →
Platform

Designed for Professional Decision-Making

Clean, information-dense interfaces built for portfolio managers and research analysts who need clarity, not noise.

Daily Signal Dashboard

Ranked equity forecasts with directional conviction scores.

Security Deep Dive

Fundamental analysis, historical signals, and forecast accuracy tracking.

Portfolio Analytics

Performance attribution, risk decomposition, and exposure monitoring.

Systematic Screener

Multi-factor screening with customizable thresholds across the full US equity universe.

Optimization Engine

Efficient frontier computation with configurable constraints on concentration, sector limits, and turnover.

Model Performance

Transparent, Reproducible Results

Every performance figure is computed on the most recent block of history the model was never trained on, separated from training by an embargo, on a factor-neutral long/short book charged with realised trading costs. The full report is regenerated automatically from the artifacts of each training run.

Out-of-Sample Window
Latest run
Net Sharpe, 1M book
—
Newey-West t, net
—
Universe
4,000+
Book
Factor-neutral L/S
Costs
Realised, net

Validation Approach

  • Factor-neutral long/short book, net of realised trading costs, out of sample
  • Newey-West significance, drawdowns, monthly returns and the leverage table
  • Calibration by score ventile, per-date rank correlation, every raw prediction
  • Full artifact set and capacity study available to qualified allocators under NDA
Open the Model Validation

Out-of-sample, factor-neutral, net of costs — with the limitations stated

Get Started

Integrate Systematic Intelligence Into Your Investment Process

Whether you manage a multi-strategy fund or a single family office portfolio, our research infrastructure adapts to your workflow. Schedule a consultation to discuss your specific requirements.

Intratio provides quantitative research and analytical tools for informational purposes only. Nothing on this website constitutes investment advice, a solicitation, or a recommendation to buy or sell any security. Past performance of any model or strategy does not guarantee future results. All investments carry risk, including possible loss of principal. Users should consult with qualified financial advisors before making investment decisions. Intratio does not hold, manage, or have custody of client funds.