Quantitative Research
Data work built to be re-run and checked: models, analysis pipelines and the tooling around them.
Scope of the practice.
Question and data definition
Agreeing precisely what is being measured, over what period and from what source, before any analysis is written.
Modelling and analysis
Statistical and quantitative models built to answer a stated question, with their assumptions recorded alongside their results.
Reproducible pipelines
Analysis that can be re-run from raw data by someone else and produce the same answer, rather than depending on a session that has since been closed.
Backtesting and validation
Where a model makes historical claims, testing them against data the model was not fitted on, and reporting what the test does and does not establish.
Research tooling
The notebooks, dashboards and scheduled jobs researchers need to keep working, built so they survive the person who wrote them.
What an engagement usually includes.
- Study design and data sourcing
- Model development and validation
- Reproducible analysis pipelines
- Research dashboards and scheduled reporting
- Written methodology and assumptions
What this is not.
Research output describes what the data shows and the limits of that finding. It is not a forecast, a recommendation or investment advice.
Every engagement starts with a written scope that states what is included, what is not, and the criteria the work will be accepted against.
Start with a conversation.
A consultation is a scoped conversation about what you need, not a sales call. You will leave it knowing whether this is the right practice for the work.