SOLVE Px (Beta): A Dramatically Different Predictive Price Dataset From SOLVE

Transcript:

What is SOLVE Px?

SOLVE PX (Beta) is dramatically different in its construction from some of the other common approaches of pricing bonds. It leverages AI (artificial intelligence) and machine learning algorithms to predict the next trade.

As I mentioned, a trade is sort of a true reflection of value because obviously it captures what someone’s willing to pay for an asset. So by purposely constructing this dataset to predict where the next trade is going to happen, we think it’s the most accurate reflection of value in a security.

The AI was constructed to leverage our quotes data, which is highly differentiated in the market. We cover all the key asset classes in fixed income, we consistently see about 20 million quotes a day across these asset classes. So the AI leverages our quotes data, it leverages trade data and reference data, and it constructs a few hundred kind of various feature inputs which are then used to train the AI model.

So, definitionally, it’s a very different dataset in its construction. And the goal of this dataset is to predict the next trade, which is definitionally the correct representation of value of a liquid asset.

Disclaimer: 

SOLVE offerings are not intended to constitute investment advice, do not seek to value any security, and do not purport to meet the objectives or needs of specific individuals or accounts.