search

ogallagher / marketsense

Leverage the human neural network to predict market asset values
Other
1 stars 0 forks source link

Expand market data to timbre mapping formula #7

Closed ogallagher closed 3 years ago

ogallagher commented 3 years ago

Now that marketsense has a basic synthesizer I’ve been able to listen to some samples generated so far and am not yet satisfied with how distinguishable each generated timbre is, despite visible changes in waveform. I believe this could be improved by using one or both of the following:

  1. Normalized market data (prices) are used as multipliers with sections of the amplitude within a period, and there’s no interpolation between each section within the period. Perhaps smooth interpolation between price multipliers will create less identically artificial-sounding tones.
  2. Part of timbre is influenced by overtones, which are defined as higher frequency component waves within the fundamental frequency, having lesser amplitude. I could try composing a unique timbre by creating overtones for each point in the market data, perhaps constraining them to be within harmonics, using Fourier synthesis.
ogallagher commented 3 years ago

I’m not wholly satisfied with the likeness between timbres generated from different random market datasets, but there’s now an extensible timbre formula system implemented with commit ac4cb06.