NNSTP-1 2009.02

Neural networks can discover patterns in data that humans might not notice and successfully predict the future trend. Addaptron Software has developed NNSTP-1, neural network computer tool, to help stock traders in predicting stock prices for short terms. NNSTP-1 predicts future share prices or their percentage changes (can be chosen in settings menu) using Fuzzy Neural Network (FNN). It operates automatically when creating the FNN, training it, and mapping to classify a new input vector. Recommended forecasting horizon is 5-10 trading days. Input data are EOD weighted closing price of the stock and the volume traded of the stock for the period that is set by user (normally, 50-100 days). The software allows using an advanced forecasting. It is based on automatic back testing scan of different inputs periods to define accuracy of each one. Then the final forecast is built on weighted averaging of all forecasts proportionally to the accuracy of each input period forecast. NNSTP-1 has a user-friendly easy-to-use interface. The software is intended for traders with a basic knowledge in stock analysis.