Movements of the stock prices, as well as price movements of other financial instruments, generally present a deterministic trend, on which are superimposed some "noise" signals, in turn composed of truly random and chaotic signals. deterministic trends can be detected and assessed by some maximum- likelihood methods. Although a truly random signal, often represented by a Brownian motion, is unpredictable, it can be estimated by its mean and standard deviation. The chaotic signal, seemingly random but with deterministic nature, proves predictable to some degree by means of several analysis techniques, among which the Artificial Neural Network (ANN) techniques have proven most effective over the widest range of predictive variables.

What is Artificial Neural Network, and what is Tradetrek Neurol-Predictor^TM?

The Artificial Neural Network (ANN) is an important branch of Artificial Intelligence. Motivated in its design by the human nervous system, ANN mimics the human nervous system in its operations. At this extraordinary interface between natural human systems and created electronic ones, ANN is capable of learning by training to generalize from special cases--just like human beings can! ANN's (supervised) simplified training and prediction process can be illustrated by the following steps—Crucial pre-processing and validation stages are discussed separately.

Stage One:

Collect the training set, which includes the input data for the ANN to "see" and the known target data for ANN to learn to output. For stock price predictions, for example, the training set and target data would naturally be historical stock prices. A vector of 100 consecutive historical stock prices, for instance, can constitute training data and with the 101st stock price as a target datum.

Stage Two:

Feed the input data to ANN; compare ANN output with the known target, and adjust ANN's internal parameters (weights and biases) so that ANN output and the known target are close to one another—more precisely, so that a certain error function is minimized.

Step Three:

Feed ANN some future input data (not seen by ANN); if ANN is well trained and if the input data are predictable, then ANN will give accurate predictions.

ANN can be trained to adapt to and solve many complicated problems, such as adaptive noise filtering, pattern recognition, and speech processing by voice recognition. ANN noise-filters are now widely used in telephone systems to reduce echo noise and in airplanes to reduce engine noise interference with the pilot's voice signal in communication instruments. [More examples of successful applications of ANN can be found in a report by DARPA (Defense Advanced Research Project Agency)]

The Tradetrek^TM Neuro-Predictor^TM is essentially an Artificial Neural Network trained for adaptive prediction of stock prices. During the prediction process, the Tradetrek^TM Neuro-Predictor^TM determines whether a particular stock is predictable with the accuracy required for a statistically significant prediction. This is accomplished, essentially, by comparing the ANN validation error against stock price fluctuations. We know that stocks with larger chaotic components and smaller truly random components tend to be more predictable than others. In addition to predicting stock prices, the Tradetrek^TM Neuro-Predictor^TM also marks the upper and lower error bounds at a given confidence level,typically 80%. In other words, the odds that the actual stock prices will fall outside these bounds are only 20%!

The Tradetrek^TM Neuro-Predictor^TM has managed to yield prediction refinements well beyond those of other systems by employing a pipelined recurrent ANN architecture (best for time-series prediction) and an adaptive supervised training procedure. More specifically, Tradetrek's ANN has been developed to incorporate the strengths of those artificial neural networks successfully used by leading research and industry leaders. ANN pre-processing is based on the Nobel Prize-winning Black-Scholes log-normal stock price model. Efficient computation algorithms have also been developed to realize Tradetrek's breakthrough in making real-time predictions.