Research series
Four reports trace a wavelet-conditioned forecasting idea from proposal to controlled re-evaluation.
Series summary
The series moves from a proposal and first wavelet-domain experiment to a complete architecture and a stricter return-domain re-evaluation.
The arc
Four reports in sequence. Each entry opens the complete original page, with its prose, figures, tables, and references preserved.
The founding concept paper. It argues that while Bitcoin's price looks like a random walk, its minute-to-minute price changes hold a near-invariant distribution a network can exploit, and proposes pairing wavelets with a GAN to extrapolate it.
Read reportThe first concrete build: a MATLAB wavelet-augmented conditional GAN evaluated in the wavelet domain across 30-, 60-, and 128-minute horizons, beating an identity baseline by up to 50.76% at 30 minutes.
Read reportThe architecture deep-dive: a full write-up of the wavelet-conditioned generator and discriminator, the compound loss, and the training and evaluation design behind the prototype.
Read reportA controlled re-test holds the earlier optimism to account. Against matched baselines, ridge regression, and residual TCNs, the neural wavelet variants do not win. This documented result reframes where to look next.
Read report