ChAI Insight

Great greater insights with a subscription

ChAI Insight gives unprecedented access to institutional views and analysis of markets on a game changing AI platform. Thousands of possibilities summarised into intelligence you can act on. Click on the links below to see examples of what we have to offer.

Metals

Aluminium

Lithium Carbonate (Asia)

Lithium Carbonate (Europe)

Lithium Carbonate (US)

Lithium Hydroxide

Lithium Hydroxide (Europe)

Lithium Hydroxide (US)

Steel HRC (Saudi Arabia)

Steel Wire Rod Common China (SH)

Tin

Zinc

Energies

Natural Gas - Henry Hub

Natural Gas - LNG (JKM)

Natural Gas - TTF

Power - German Baseload (EEX)

Power - UK Baseload (EEX)

RBOB

WTI

Agriculturals

Wheat (Paris Milling)

Plastics

LLDPE

PVC

Forest Products

Frequently asked question?

Still have a question?

Do your models/algorithms change for time horizons? (short term/long term)?

Yes. We use different models for different time horizons and for different commodities. However, the models have a fairly similar high-level construction across the different horizons they work over.

What is unique about what you do? Aren’t large hedge funds already doing something similar?

Large systematic asset managers will be making predictions of commodities prices using alternative (and standard) data in the same way as us. However, they will be turning these predictions into trading signals that are optimised for their own use case (i.e. taking into account trading costs, interactions with other assets in their portfolio, risk constraints etc) and are less interested in raw predictive accuracy, untangling how the predictions are derived so that various assumptions can be played around with nor selling these predictions on.

What kind of AI techniques are you using?

We are using a variety of machine learning models at different points in our prediction processes, for example Gaussian Processes, Support Vector Machines, LASSO and Multi-Task Learning.
Aside from prediction accuracy, we also believe it is very important for our predictions to be explainable, hence our choice of techniques

Our Risk / Compliance Department is concerned about model transparency - How do you ensure your models can be explained?

We are motivated by explainability and also the ability to control our sensitivity to various inputs so that users can up/down weight the importance of economic data, currency movements, demand/supply information etc.

Can you expand on how the AI is used and how it's a differentiator?

At a very high level it's used to integrate a variety of data sets that are pretty different to each other in nature (text, images, freight movement, economic time series) and sampled at different frequencies (daily, weekly, monthly etc), and in some cases not even consistently themselves (for example satellite imagery because of cloud cover). Furthermore, the data often has a very low signal to noise ratio and has a prognostic ability that changes with time, so that relationships between our inputs and what we are trying to predict changes.