PROJECT: TRADING

Challenges

The traders relied on personal and company wide spreadsheets / balance sheets, informal chat channels, public chat forums, public and private data sources.
The datasets were unstructured, sometimes messy and fragmented.
Multiple systems and databases, manual spreadsheets, silos.
People could miss data and make biased, emotive and ill-informed trading decisions.
There were inconsistent data standards across regions, including languages, units, estimates v actuals, unreliable risk adjusted datasets, number extraction and risk patterns extracted from words.
Some of the data required heavy processing, e.g. weather, yields, NASA.
Decisions needed to allow for structural breaks such as wars, sanctions, tariffs, extreme weather etc.
Protecting IP, confidential information, trade secrets and formulas within the client’s balance sheets.
Building a clean, real-time, unified data layer can be resource intensive.

Solution

Zai Node delivered a hybrid solution which was a human-led strategy with AI-augmented decision support and automated operational optimisation.
The first major data fragmentation challenge was solved by our engineers and data scientists building a centralised data lake which auto pipes real time and manual data (e.g. markets, shipping, weather, crop yields, stock reports, credit).
Using a VLM and LLM to extract data from unstructured sources including satellite imagery and public chat forums in many languages.
We standardised and cleaned the data and created a “single source of truth”. We think of this as a “digital twin” of a commodities trading balance sheet.
Used ML to help detect structural breaks from extreme events and stress-test the client’s models under historical crises, looking for probability and anomaly detection.

Impact

Data pipeline solution improved decision making speed and realiability, and eliminated spreadsheet risk. 1–3% improvement in trading margins from speed and less errors, and a 30% reduction in operational time and resources.
Institutional knowledge is captured instead of lost. It becomes codified, measurable, repeatable and scalable, moving from a individual balance sheet approach.

Upshot