Structured Funds

The tactical system operates on a granular, minute-level chart and is designed to detect short-duration, high-frequency ghost patterns—signals that may only persist for seconds—allowing for precise intra-day execution and potential alpha capture on compressed timeframes.

Our objective in this phase is to conduct a documented live trading test of the tactical engine and analyze its real-time performance. Upon completion, we will proceed to Phase IV: capitalizing a fund 10x larger to trade the full-sized E-mini Nasdaq futures contract, which carries 10x the notional exposure of the Micro contract. This stage will enable us to conduct a more extended test, further validate the model, and generate a detailed performance record.

Currently in progress…

At the core of the platform is the Bimini Road AI engine, which detects ghost patterns—statistical anomalies within live market data that indicate the presence of informed trading. These patterns provide a unique lens into real-time market behavior often associated with material non-public information.

Our investing strategy takes advantage of our tactical and strategic predictive models.The tactical model is an evolution of our original strategic ghost pattern framework, which identified directional signals based on longer-term accumulation patterns—often spanning 30 to 50 days before generating a conviction-level prediction.

By using both models we can further reduce risk by allocating long term capital while taking advantage of short term trends during intraday trading.Our strategy is both orthogonal (non correlative) and bi-modal.

Orthogonal trading refers to strategies designed to deliver returns that are statistically uncorrelated—or only minimally correlated—with broader market indices and conventional asset classes. Our approach is driven by a proprietary predictive signal that exhibits non-linear, non-recurring patterns in both timing and asset selection. As a result, the strategy's return profile should not be expected to demonstrate meaningful correlation with traditional market benchmarks.

Our trading framework integrates a dual-layered risk management architecture. The AI system is capable of identifying anomalous trading patterns—referred to as “ghosts”—that may signal underlying market inefficiencies or in our case non-public information trading. These signals are categorized by velocity: slow-moving ghosts are observed over multi-day to multi-week horizons, while fast-moving ghosts are detected and responded to in real time, within seconds or minutes. This structure enables dynamic risk calibration across varying time horizons.