The BrainTrader system learns from cause and effect relationships. A simple sports analogy may help to better understand the way our system learns. Imagine you are learning to play golf for the first time. You have never even picked up a club before. You don't know how to grip the club, or which club to use to hit the ball into the fairway. Furthermore, you don't know what the trajectory of the ball will look like after you make contact. Will it slice? Will it hook? Will the wind have a significant effect on the trajectory of the ball? Where do you need to aim to avoid the water hazard? Needless to say, there are thousands of independent variables that influence the physical mechanics of the game.
So, ask yourself this question: Before you go out onto the golf course, are you going to sit down and run calculations based on the laws of physics to account for all of these factors? No, of course not, you use what little information you already have about the sport and swing at the ball. Perhaps the first time you swing at the ball, you lift your head and you completely miss it. You realize your error and make a correction. The next time you keep your head down and make contact, but because of the angle of the club, the ball sails into the woods. Over time, through trial and error, you continue to make corrections until you find that the ball starts to go where you were aiming.
Practice makes perfect. The way a person learns to play golf is similar to how the BrainTrader software learns. When forecasting the direction of an index, our Neural Network analyzes a large amount of historical data and attempts to make a forecast as to what will happen next. It then compares its forecast with what really happened and makes adjustments to compensate for any error. Essentially, the Neural Network "lives" through history time after time until it becomes proficient at forecasting the future. In essence, the program has learned what factors have significant effects on the future prices of the indexes. Some of the factors that affect prices are hidden and are not easily recognized. But they exist nonetheless. The BrainTrader program learns what the cause and effect relationships are and it is then able to quantify how much of an effect each factor will likely have on an index.
If you would still like to learn more about Artificial Neural Networks and their financial applications, we recommend you read the book the creator of our system wrote on the subject: "Financial Prediction Using Neural Networks", by Joseph S. Zirilli. There are also many online resources you may find by searching for "neural networks" through a search engine.
Home | About Us | Investing | Concepts | Account Info | Performance | Contact Us 
