This website presents academic research and analytical tools for informational purposes. It does not constitute financial advice. Results may vary. This website presents academic research and analytical tools for informational purposes. It does not constitute financial advice. Results may vary.

What if your model is wrong about tomorrow?

Structured programs for professionals who want to build portfolios that survive when assumptions break.

Most frameworks assume you know the distribution of returns. Our team does not. We teach multiperiod ambiguity aversion — the discipline of deciding when you admit you do not know the odds.
Analytical team reviewing robust portfolio models

Programs built for practitioners

From foundational ambiguity theory to advanced multiperiod optimization, each program is designed for working professionals who need practical tools, not abstract lectures.

1

Ambiguity foundations

Start with the axioms. This program introduces recursive multiple-prior utility, robust control theory, and the difference between risk and ambiguity. Participants learn to recognize when standard models assume more knowledge than anyone possesses. The material draws on seminal papers and recent advances, with exercises that translate theory into diagnostic questions you can ask your own models.
2

Multiperiod optimization

Move from single-period robustness to dynamic frameworks that adapt across horizons. This program covers minimax regret, robust Bayesian updating, and time-consistent ambiguity averse preferences. Participants build and stress-test multiperiod models using real market data, learning where elegant theory breaks in practice and how to patch it.
3

Practitioner certification

A rigorous assessment track for professionals who want to demonstrate mastery of ambiguity-aware portfolio construction. The certification covers model diagnostics, robustness testing, and communication of uncertainty to investment committees. It is not a badge for completing videos. It is a credential earned through applied work reviewed by our research team.
4

In-house advisory

For teams that need a shared language around model uncertainty. We design custom engagements that map your specific analytical challenges onto robust frameworks. The output is not a report that sits on a shelf. It is a working model your team can maintain, stress-test, and explain to stakeholders who ask hard questions.

Your path forward

Three stages from first principles to practical implementation.

Step 1

Understand the limits

Learn to distinguish risk from ambiguity. Build the habit of asking what your model assumes, what it ignores, and how badly it fails when those assumptions break.

Step 2

Build robust tools

Construct multiperiod frameworks that optimize across sets of plausible models rather than betting on a single forecast. Test them against historical regime shifts.
Step 3

Implement with clarity

Translate robust outputs into position sizing, hedging decisions, and committee presentations that acknowledge uncertainty without paralyzing action.

Common questions

Participant outcomes

What professionals say after working with our frameworks.

March 2026

Marcus Okafor

Quantitative analyst, Meridian Research

Challenge

Single-period models failed during correlation spikes in volatile markets.

Outcome

Built a multiperiod robust framework that adapts to regime shifts and reduces tail exposure.

"The multiperiod optimization program changed how I think about model risk. I used to calibrate once and hope. Now I build sets of plausible models and optimize across them. The stress-testing module alone was worth the time."

12 weeks
January 2026

Priya Natarajan

Risk officer, Aurora Capital

Challenge

Investment committee demanded clearer language around uncertainty in portfolio decisions.

Outcome

Learned to communicate robust outputs and ambiguity bounds in accessible terms.

"I needed to explain why our positions looked conservative. The practitioner certification gave me vocabulary and tools to show the committee exactly what we did not know and how we protected against it. The credential carries weight."

16 weeks
November 2025

Henrik Bakker

Portfolio strategist, Nordic Foresight

Challenge

Existing tools assumed known return distributions that repeatedly proved wrong.

Outcome

Replaced point forecasts with robust Bayesian filters that update as evidence changes.

"The ambiguity foundations program was humbling in the best way. It forced me to list every assumption my models buried. Some were defensible. Many were not. Rebuilding with explicit uncertainty sets improved my worst-case outcomes significantly."

10 weeks
August 2025

Yuki Tanaka-Olsen

Research director, Pacific Edge

Challenge

Team lacked shared framework for discussing model uncertainty across asset classes.

Outcome

In-house engagement established common robust methodology and diagnostic practices.

"Our team argued about models but never about assumptions. The custom engagement gave us a shared language and a working robust framework we still use. The research team was patient, rigorous, and focused on what we could actually implement."

8 weeks

Ready to build portfolios that survive bad assumptions?

Request a detailed syllabus, speak with an academic advisor about program fit, or explore how our team can design a custom engagement for your organization.