Bridging the gap between contracts, with data rather than guesswork
Netropolis runs backtested AI models that manage surplus business capital for freelancers and consultants, aiming for steady, measured growth in the periods between paid work.
Netropolis runs backtested AI models that manage surplus business capital for freelancers and consultants, aiming for steady, measured growth in the periods between paid work.
Independent income arrives in uneven bursts. A strong quarter leaves cash sitting in a current account, earning little, while the next invoice date remains uncertain. Most contractors default to holding everything in reserve, which is safe but static, or to ad-hoc investing, which is rarely tested against anything beyond personal judgement.
Netropolis was built around a narrower question: what does the historical data actually suggest about allocating that surplus, and how quickly can it be converted into a specific, risk-adjusted recommendation.
The process is deliberately linear. Each stage exists to remove discretion from the decision and replace it with a documented, repeatable step.
Market, macro, and liquidity datasets spanning over a decade are collected and normalised before any model is permitted to touch them.
The AI builds a probability-weighted view of likely outcomes under varying volatility conditions, rather than a single forecast.
Allocations adjust within agreed thresholds as conditions shift, with every change logged against the original strategy brief.
Rather than a static quarterly report, the platform re-reads relevant market signals as they occur and reflects any material shift in your allocation's risk profile within the same day.
During periods of elevated volatility, the model is designed to reduce exposure ahead of confirmed downturns where historical patterns support it, with the explicit aim of limiting drawdown rather than maximising short-term gain.
You indicate how soon capital may be required, and the recommendation set adjusts accordingly, favouring shorter-duration, lower-volatility positions where near-term liquidity is a stated priority.
We do not publish client quotes. Instead, every strategy comes with a methodology brief describing exactly what was tested, against which data, and over what period.
Each strategy ships with a chart comparing simulated performance against a relevant benchmark, including periods of loss.
Datasets include FTSE 100 historicals, global macro indicators, and sector-level volatility measures, documented alongside the model's assumptions and known limitations.
All strategies are simulated against more than ten years of market data before deployment, and re-tested whenever the underlying model is revised.
Netropolis was created around a specific observation: independent professionals in the UK often hold meaningful reserves for short, unpredictable periods, and existing investment tools are built for either long-term pensions or active day-trading, with little in between.
Our approach combines backtested AI models with straightforward reporting, so that a contractor can understand not just what the recommendation is, but why the data supports it.
You can flag a portion of capital as reserved, for example funds set aside for corporation tax, and the model will exclude it from active allocation, keeping it in lower-volatility, readily accessible positions by default.
Account data is encrypted in transit and at rest, and access to allocation controls requires authenticated sign-in. We do not share client-level data with third parties for marketing purposes.
Model outputs are reviewed continuously, and any recommended change to your allocation is presented with the supporting data the same day it is identified. You retain final approval before any rebalancing takes effect.
Review the backtested models relevant to your liquidity horizon before committing any capital.