| Home | Forecasts | Data | Research | Extended Forecasts |

The Method Behind The Madness

The Financial Forecast Center uses a state-of-the-art artificial intelligence technique called "neural networks" to predict the behavior of the U.S. and global financial markets and economies.  Neural networks enable a computer to truly learn from a set of data to allow pattern recognition and to formulate generalizations. The name "neural networks" is used to describe the computer programs because they are based on the operation of a network of nerves, such as the human brain.  These computer networks learn much the same way a network of nerves learns.

Because a computer is allowed find its own patterns and generalizations in the data set it reaches its own conclusions and essentially eliminates or side-steps the limitations in man-made forecasts or models--the limiting nature of the theories and assumptions on which the models are based. This technique allows for a more objective model to develop which is not biased by human preconceptions creative embellishments or cognitive limitations.

The training sets use the following economic values as the foundation for developing the models on which the forecasts are based:

§ Employment
§ Gross Domestic Product
§ Industrial Production
§ Retail Sales
§ Fixed Investment
§ Money Supplies (M1 and M2)
§ Personal Income
§ Business and Personal Savings
§ Imports and Exports
§ Loans
§ Foreign Currency Exchange Rates
§ Global Stock Market Indices
§ Various U.S. and International Money Rates
...And many more.

And of course, the predictions from the models are considered against the historical movement of an index, indicator or stock as a double check. If the models predictions are truly unrealistic, they are reformulated and rerun.  We do not try to censor the forecasts except in extreme cases since this is returning the potential for human bias into the loop.

Neural networks are hard at work in many different industries and services such as credit approval, voice recognition, weather forecasting, securities forecasting, and product development/design.