Where stochastic modelling fits on a long engagement.

Choosing the process is the substantive modelling decision. Geometric Brownian motion assumes continuous paths and lognormal returns; real markets jump and have heavier tails than that implies. The choice encodes a belief about how the world behaves, and it is where model risk originates.

Calibration to historical data carries the assumption that the future resembles the past. That assumption is reasonable in stable conditions and fails precisely during the events the model exists to quantify, which is why stress testing outside the calibration range matters more than fit quality inside it.

What an assigned team does with stochastic modelling.

Models used for decisions of consequence need governance: documented assumptions, independent validation, and periodic review. In regulated sectors that is a requirement; everywhere else it is simply prudent.

Building that governance alongside the model rather than after it is part of how quantitative work is scoped, and what it involves is set out in how the monthly fee is built.

What we use stochastic modelling for.

  • Processes chosen for the actual behaviour Jumps and heavy tails represented where the data shows them.
  • Stress testing beyond the calibration range Behaviour examined under conditions the history does not contain.
  • Assumptions documented for validation A model that an independent reviewer can assess rather than only run.

How stochastic modelling capacity is assigned.

Quantitative modelling capacity is assigned under data engineering outsourcing, with model governance treated as part of the deliverable.

Tell us what your roadmap needs stochastic modelling for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

Loading the contact form… You can also email hello@azendo.co.

We reply within one working day. No obligation, and no newsletter.