Skip to content

Northstar Capital · Systematic investing

Rules decided in advance. Evidence before conviction.

Northstar Capital is a one-person business that researches, tests and operates rules-based investment strategies. This site shares the non-proprietary part of that work: the ideas, methods and operating practices behind a systematic fund, written for anyone who wants to build one.

Read the field notesAbout the business

How the work is done

Research

Hypotheses are written down before they are tested. Every trial is counted, results are judged after realistic costs, and history the design never saw is kept back for the final check.

Engineering

Strategies are software. They run from reproducible builds with explicit invariants, and every input and decision they make is recorded automatically.

Operations

A live book is monitored every day, reconciled against its own simulation, and watched by alerts that are rare enough to be acted on.

Knowledge Centre

Field notes

A numbered series of technical notes on building and running a systematic fund, with primary sources for every claim.

No. 01Market anomaliesWhat they are, why some of them persist, how they have held up, and how not to fool yourself when looking for new ones.Foundations · 18 min readNo. 02Volatility targetingSizing positions by forecast risk to keep the risk carried roughly constant, and where the rule stops protecting.Foundations · 20 min readNo. 03Indicators, and the 200-day moving averageWhat technical indicators measure, how to test one honestly, and a century of daily data on the most famous of them.Intermediate · 15 min readNo. 04QuantConnect and LEANAn open-source engine, a hosted platform, and what a practitioner should know before trusting either.Foundations · 9 min readNo. 05Execution: TWAP, slicing and jitterWhy orders are split over time, how execution is benchmarked, what market impact costs, and why good schedules are deliberately irregular.Intermediate · 13 min read

In preparation: structuring a fund, sleeves, the backtest mill, notifications, monitoring a live book, live versus backtest reconciliation. See the series

Principles

Four rules the practice runs on

  1. 01

    Decide before you look

    Targets, rules and the conditions for abandoning an idea are fixed before the backtest, not after it.

  2. 02

    Count everything

    Every trial, every cost and every gap between live and simulated results is measured, because what is not counted cannot be corrected for.

  3. 03

    Size for the bad day

    Risk is set by what can plausibly go wrong, not by the average day.

  4. 04

    Prefer robust to clever

    Broad, simple rules that work across many settings beat finely tuned ones that work at one.