Background
About Our Team

Where Quantitative Insight Meets Machine Learning Precision

Built by practitioners who saw the gap between raw market data and actionable dispersion intelligence
A team of former market makers and researchers set out to solve a problem they knew intimately: the difficulty of spotting when individual names diverge from index behavior in ways that create measurable opportunity. What began as internal tooling became a platform for traders who demand rigor.

Purpose-Built Dispersion Detection

Engineered for volatility surface anomalies

The platform surfaces situations where implied correlation shifts create asymmetric payoff structures, delivered through an interface designed for decision speed.

Research-First Culture

Every feature originates from a documented hypothesis and survives a structured validation protocol before reaching production.

Practitioner Founders

The leadership team has spent years inside institutional trading environments, experiencing the same detection challenges users face.

Continuous Model Refresh

Signal decay is assumed, not ignored. Models are retrained and backtested on a scheduled cadence to preserve relevance.

Transparent Methodology

Users see how signals are constructed, what inputs drive them, and where uncertainty remains in every output.

Real-Time Signal Feed

Dispersion alerts are generated throughout the trading session as market conditions evolve, not batched at arbitrary intervals.

Customizable Filters

Users define their own thresholds for correlation breakdown, sector concentration, and volatility regime to match their specific mandate.

Multi-Asset Coverage

The detection engine monitors equity indices and their constituents across developed markets, with expansion underway.

Historical Context Layer

Every current signal is presented alongside analogous past episodes, so users understand whether conditions are typical or exceptional.

Our Beliefs

What Drives Every Design Decision

The team operates from a small set of convictions that shape how the platform is built, how signals are validated, and how users are served. These are not slogans. They are constraints.

Meet the team
  • Markets exhibit structural patterns
  • AI amplifies trader judgment
  • Signal decay is inevitable
  • Transparency builds trust

The People Behind the Platform

  1. 01 Co-Founder and Chief Research Officer
    Dr. Elena Vasquez-Chen

    Dr. Elena Vasquez-Chen

    Elena spent a decade designing volatility models for a global market-making firm before returning to academia to study how machine learning could improve correlation forecasting. Her research on regime-switching behavior in equity dispersion became the foundation for the platform's core detection engine. She holds a doctorate in financial econometrics and continues to supervise graduate research in quantitative methods.

  2. 02

    Co-Founder and Head of Platform Engineering

    Marcus Whitfield-Okafor

    Marcus Whitfield-Okafor

    Marcus led infrastructure teams at two systematic trading firms, where he built the low-latency systems that processed millions of market messages per second. He joined Elena to solve a different challenge: making sophisticated dispersion analytics accessible without sacrificing the computational rigor that institutional traders require. He oversees all platform architecture and data pipeline design.

  3. 03 Head of Model Validation and Risk
    Sarah Brennan-Liu

    Sarah Brennan-Liu

    Sarah began her career in model risk management at a major investment bank, where she developed frameworks for validating quantitative tools used in derivatives pricing. She ensures every signal produced by the platform has been stress-tested across multiple historical regimes and that users understand the limitations of each output. She holds advanced degrees in statistics and financial engineering.

Our Path

From a research question to a platform used by traders who refuse to guess

2019

The Research Question

Elena published a paper on regime-dependent correlation breakdowns in equity indices. The findings attracted attention from former colleagues who asked whether the method could be operationalized into a real-time tool.

Research Publication
2021

Prototype and Early Testing

Marcus and Elena built the first detection prototype and shared it with a small group of former institutional traders. Their feedback reshaped the signal format, adding context layers and historical analogues that made outputs immediately actionable.

Prototype Feedback
2023

Platform Launch

After two years of iterative refinement, the platform launched with coverage of major developed-market equity indices. The founding cohort of users remains actively involved in product direction through a structured advisory program.

Launch Advisory
2025

Expanded Coverage and New Models

The team introduced additional detection methodologies and expanded asset coverage. A dedicated model validation function was established under Sarah's leadership to formalize the standards that govern signal quality.

Expansion Validation
A brief history

Recognition and Partnerships

2023

Fintech Innovation Award

Honored for advancing the application of machine learning to volatility surface analysis in institutional trading environments.

2022

Quantitative Research Publication

Core methodology peer-reviewed and published in a leading journal covering financial econometrics and derivatives modeling.

2024

Academic Partnership

Collaboration established with a research university to advance graduate training in computational finance and market microstructure.

2025

Data Provider Integration

Selected for an early-access program by a major market data vendor to test next-generation analytics delivery infrastructure.

How We Work

Four commitments that shape every interaction with clients, partners, and the market data we analyze

1

Intellectual Honesty

Every model is presented with its known limitations. When a signal underperforms, the team investigates publicly and shares findings with users rather than obscuring unfavorable results behind marketing language.

2

Transparent Communication

Users receive clear explanations of how outputs are generated, what assumptions underpin them, and which market conditions might reduce their reliability. No black boxes, no hand-waving.

3

Continuous Research

A fixed portion of resources is allocated to exploratory research regardless of near-term commercial priorities. The team believes that maintaining this commitment is the only defense against signal decay.

4

Ethical Deployment

AI tools in financial markets carry responsibility. The platform is designed to support informed decision-making, not to automate risk-taking or encourage behavior that users do not fully understand.