Our Embedded Intelligence Platform (EIP) leverages proprietary learning algorithms to model cause and effect in complex systems. We believe that understanding a system’s behaviour requires more than just modelling the correlation between variables. Instead, our technology observes the system directly through its time series data, modelling its causal evolution from an initial state shift to a resulting directional change. Imagine a complex system as a still pond. A pebble’s impact is the cause, creating a ripple that expands into waves, representing the effect. By observing the pond’s turbulence data, our algorithms can identify the initial shift and trace its progression without needing external context about who threw the pebble or where it was thrown from. By extending Takens’ Theorem, we’ve developed an entirely new way to understand complex systems. Our parameter-free algorithms require no training data or continuous retraining. They autonomously reconstruct the full picture of a complex system from a single time series, revealing the true causal drivers behind its behaviour. This deeper understanding fundamentally changes model development, enabling real-world applications in finance, weather, and beyond.

​
Python Package

To install the sumtyme Python package, you’ll use pip, Python’s standard package manager. Just run the following command in your terminal: 
pip install sumtyme

​
Python Quickstart - Finance

Model Environment

Analyses the environment to forecast a directional change for the final period.

Forecast Change

Forecasts a directional change for the final period.

Rolling Forecast

Performs a rolling analysis to identify evolving trends.

Identify Causal Chains

Analyses different timeframes to identify causal chains.

​
Demonstrations - Finance