The Algorithm

I Know First Currency Forecast Algorithm

Currency-prediction.com uses a state-of-the-art predictive algorithm that is based on Artificial Intelligence (AI), Machine Learning (ML), Artificial Neural Networks, and Genetic Algorithms. The impartial algorithm capitalizes on the inherent predictability of the stock market resulting from short-term uncertainty, irrational human behavior, and differing fundamental asset valuations.

algorithm

 

Currency-prediction.com models and predicts the flow of money between various markets and separates the predictable part of assets from stochastic (random) noise. It then creates a model that projects the future trajectory of the given market onto the multidimensional space of other markets. The system outputs the predicted trend as a number, positive or negative, along with the wave chart that predicts how the waves will overlap the trend. This helps the trader to decide which direction to trade, at what point to enter the trade, and when to exit.

The model is 100% empirical, meaning it is based on historical data and not on any human derived assumptions. The human factor is only involved in building the mathematical framework and initially presenting to the system the “starting set” of inputs and outputs. From that point onwards the computer algorithms take over; they constantly propose “theories” and test them automatically on years of daily market data, then validate them on the most recent data, which prevents over-fitting. Some inputs are being “rejected”, meaning they don’t improve the model. Then another input could be substituted. This bootstrapping system is self learning, and thus live. The resulting formula is constantly evolving, as new daily data is added and as a better machine-proposed “theory” is found.

Some stocks are forecasted by several independent models. Thus multiple predictions can be obtained, based on different data sets. Additionally, each model consists of a number of sub-models, each giving an independent prediction. If the sub-models give contradictory predictions, this should be a warning sign. Six different filters are also employed to refine the predictions.

Chaos, a non-linear evolving system, plays a large role in moving the stock market. Though chaos is not random, it is often counterintuitive and thus is often misinterpreted. Quasi-deterministic chaos is responsible for creating waves in the market that are predictable and analyzable with processes developed in complex mathematics and quantum physics. Even though the Heisenberg Uncertainty Principle says that it is impossible to precisely record both the momentum and position of an electron at the same time, the properties of an agglomeration of multiple electrons, or waves, is well understood. Similarly, it is difficult to analyze individual transactions in the stock market (quanta), but it much easier to interpret long-term trends (waves).

Comments are closed.