Range Bound Levels using Neural Network
Neural Network
Predicting stock and futures prices is a challenging task due to the chaotic nature of financial markets. To tackle this complexity, I developed a neural network model using Python, leveraging its ability to capture non-linear relationships and hidden patterns in the data. I process three different time periods of data to include more recent to more historical data. The accuracy of this model is often within 1 or 2 points for futures. You can see an example to the right.
Sinusoidal Signal Processing System
Sinusoidal Signals
In this model I filter data from the stock market using a variety of filters. Each time it loops through a list of filters to determine which is the most accurate for that specific stock, futures, or crypto asset. Then transform the data into a frequency. I attempt to model the data to reprensent a Sin graph. Y=Sin(X)
Doing this gives us another attempt at finding patterns in chaotic data series and a unique visualization.
