Artificial Intelligence (AI) systems have had varying degrees of success when measured against humans. In problems such as chess, which succumb to sheer computational firepower, the machines have advanced greatly in a short time.

Like chess, financial markets operate under the supposition of rational participants. Humans are supposed to be calculating the odds, maximizing return and minimizing risk.

If this were indeed the case, artificial intelligence trading software would stand a good chance at bettering its human counterparts in making and capitalizing on market decisions. Unfortunately, rationality is not always the best assumption for either humans or markets. One needs to look no further than the current economic situation to observe how irrational human traits like confidence, fear and greed play out in market dynamics. The uncertainty injected by the human participants makes the markets much harder to predict.

Back Propagation Neural Network

However, artificial intelligence trading software can be successfully applied to certain trading functions, specifically intermarket analysis. An invention by Louis Mendelsohn relates to methods and systems for performing intermarket analysis using neural networks. A neural network is a system of programs and data structures that approximates the operation of the human brain. (Learn more about Neural Networks here.)

Mendelsohn’s invention details proprietary methods and processes for selecting from a large pool of available global financial markets. These are the related markets that have the highest relevance in training neural networks to make market forecasts for each ‘primary’ market with a high degree of predictive accuracy. This selection process includes determining ‘key’ intermarkets, ‘general’ intermarkets, and ‘predictive’ intermarkets from the pool of available markets that correspond to each ‘primary’ market.

Neural Network Software

Market data for each of the key intermarkets, the general intermarkets and the predictive intermarkets can then be processed to train neural networks so that when the neural networks process this input data, predictive output data generated by the neural networks for each primary market are as accurate as possible.

After training the neural networks, all relevant market data for each primary market can be processed with the neural networks to predict future market data. That data is then used to arrive at a predictive technical indicator for use by the trader in making trading decisions.

This process drives the VantagePoint software so humans can make rational trading decisions to master the markets.

VantagePoint Software Demo