Trading systems research · Our own capital

Getting a result is one thing.
Knowing what it proves is another.

Quantic Eagle builds trading systems: programs that turn market analysis into decisions about what to buy or sell and how much. We trade only with our own capital; we do not raise or manage other people’s funds. Here we share cases that help you understand and check those decisions.

Two predictions right out of three. One account loses.

The prices and predictions are made up for this exercise. They are not Quantic Eagle trades or results.

Same predictions. Why does one account gain and the other lose?

Here we compare two settings of the same trading system: a program that reads price predictions and calculates purchases, sales and an account balance. The predictions stay the same. Only the amount used for the third purchase changes.

All three predictions say the price will rise; the third is marked as more convincing. One setting always buys €1,000 worth. The other uses €2,000 for that third prediction. Both accounts start with a simulated €10,000; the trades happen one after another and each costs €2, including the sale.

Account balance after each tradeSimulated balance after each completed trade. The lines overlap through the second trade; a different purchase amount changes the loss on the third. €1,000 every time: €10,000, €10,018, €10,026, €10,004. Variable amount for the third purchase: €10,000, €10,018, €10,026, €9,984. The vertical axis zooms in on differences of a few dozen euros. The starting account balance is €10,000. The prices and predictions are made up for this exercise. They are not Quantic Eagle trades or results.−200+20+30Change from starting balance · €StartTrade 1Trade 2Trade 3+4−16
The vertical axis zooms in on differences of a few dozen euros. The starting account balance is €10,000.
€1,000 every time€10,004Result after costs: +€4
Variable amount for the third purchase€9,984Result after costs: −€16

The price rises in 2 out of 3 cases, with both settings.

Follow the money in the third purchase

The price falls from 100 to 98: a 2% loss. With €1,000 invested, you lose €20 plus €2 in costs. With €2,000 invested, you lose €40 plus the same €2 in costs. The first two trades made €26 after costs. That is why one account finishes €4 up and the other €16 down.

“The model was right twice out of three” leaves out exactly this difference. When comparing versions of your system, check how much each buys. Otherwise, you may attribute a change to the model when it arose after the prediction.

Open the interactive case →

Two charts to explore losses and costs

01 / Risk along the way

Same endpoint. Different risks.

Illustration · invented data

Two paths can finish at the same level after exposing capital to very different losses.

  • Path A
  • Path B
Same endpoint. Different risks. — Illustration · invented dataTwo invented paths share the same starting and finishing level. Path B falls further from its peak and has not returned to that peak by the end.
Path B falls much further from its peak. Its final rise still leaves it below that peak. Looking only at where the two paths finish would miss this difference.
Depth
How far does it fall from its peak?
Duration
How long does it stay below that peak?
Recovery
Does it regain the peak within the period observed?

02 / Testing the assumptions

What happens when conditions change?

Illustration · invented data

A promising result may depend on low costs or execution that is hard to achieve. Those assumptions need testing too.

  • Reference assumptions
  • Higher costs
  • Less favourable execution
What happens when conditions change? — Illustration · invented dataThree invented scenarios share an initial path. Once the assumptions change, the paths with higher costs or less favourable execution diverge from the reference path and finish lower.
In the final part of this example, higher costs or less favourable execution reduce the gain and can turn it into a loss. These are invented scenarios, not forecasts or results from our systems.
Costs
Does the result hold up under less favourable assumptions?
Execution
Are the prices, timing and liquidity realistic?
Context
What changes in a different period?

Brand film · 49 seconds

Our capital.
We answer for every decision.

Four checks to make sense of your test.

What change do you want to try?

If you add a rule to skip some purchases, compare the program with and without that rule. Use the same data so you can see what the change actually did.

Had that information arrived yet?

Suppose you make a decision on Monday at 10 am. News published at noon could not have helped, even if both entries have Monday’s date in your file.

What is left after the costs?

A simulation can look promising until you include fees and less favourable purchase prices. Run the numbers again before drawing a conclusion.

What do you really need to repeat?

If you change only the rule for choosing purchases, you may be able to reuse scores you have already calculated and checked. Repeat every test that depends on the new choice, though.

Changed the rule? Keep the previous version too.

On day 15 you add a rule and run the simulation again from the start of the month. The new chart can help you understand the change. It does not show what the program actually decided during the first fourteen days, when it was still using the old rule.

  1. Keep the decisions the program made at the time.
  2. Save the past rerun with the new rule separately.
  3. From now on, record which version you are using.

The prices and predictions are made up for this exercise. They are not Quantic Eagle trades or results.

IN PREPARATION · FREE RESOURCES AVAILABLE NOW

Turn your trading idea into a system you can test.

Before Capital is the practical fieldbook we are preparing for readers who already work with data and statistics. It takes you through choosing data, building tests and comparing versions of your system. The free cases are available now: follow the calculations and try the questions for yourself.

Open the interactive case →

Guide & tools · Open research desk

Research note · Market structure

Market efficiency is not binary.

A practical note on how information becomes price, why competition compresses opportunity and why systematic research is ultimately a test of what survives beyond the historical sample.

Read the research note

Clear boundaries

What Quantic Eagle is—and is not.

Clarity is part of the operating discipline. Quantic Eagle is built to deploy its own capital and to keep research, execution and governance inside a controlled perimeter.

Is

A proprietary systematic investment company.

  • Operates exclusively with company capital
  • Develops and operates quantitative investment infrastructure
  • Conducts research, selection and operations internally
  • May engage selectively on corporate and strategic matters

Is not

A public investment proposition.

  • Does not accept or manage third-party capital
  • Does not offer investment advice or accept client mandates
  • Does not sell signals, models, trading execution software or execution access
  • Does not publish operational secrets or account-level data
  • Is not authorised to manage third-party investment capital or provide regulated investment services to clients, and does not offer those services.

Understanding roles and relationships between owners

Looking into joining an existing company or working with its founders? We’ve brought those articles together in a separate reading path.

Understanding roles and relationships between owners
Educational note · 02

Investing in a company that already exists

Build, buy or back? A guide to what ownership means, what more capital changes and what risks remain.

Read the note on private company ownership
Educational note · 03

Joining an existing startup as a partner

Equity, capital, responsibilities and the questions to resolve before joining.

Read the note
Educational note · 04

After a startup: start again or join?

How to assess what happened and choose the next stage of an entrepreneurial career.

Read the note
Educational note · 05

Late co-founder, investor or employee?

Separate the title from ownership, work, capital and authority.

Read the note

Selective external dialogue

We are not seeking mandates. We remain open to substantive strategic conversations.

Quantic Eagle may consider confidential corporate, strategic or infrastructure discussions with relevant counterparties able to evaluate the company, its quantitative IP and its operating platform. These discussions concern the company or strategic cooperation and are distinct from accepting capital to manage on behalf of others. Nothing on this website constitutes a public offer of shares in Quantic Eagle LTD.

Company & strategic enquiries

Company & strategic enquiries

A direct channel for relevant conversations.

Please provide enough context for us to assess your enquiry. This channel is for corporate, strategic and infrastructure matters. It does not handle requests for investment management, retail investment, signals or trading execution software.

Legal entity
Quantic Eagle LTD · Company no. 14897160
Registered office
71–75 Shelton Street, Covent Garden, London WC2H 9JQ, United KingdomStatutory registered office and correspondence address. Quantic Eagle operates through a digital working model; this address is not presented as a physical trading floor.
Official record
Companies House ↗
Contact channel
Company & strategic enquiries via the form

Protected by standard security and anti-abuse controls. Please do not include account credentials, trading data or other sensitive material.

Back to top