It is also important to note what we do not see: the lack of any oscillatory term in the formula (sin, cos, etc) hints at the lack of strong regularities (periodicities) during the eight months of the analysis.
The other valuable observation here is that in the absence of access to many of the Ripple ledger statistics that will normally allow identifying large holders, the usage of the wallet allows to single out the mid-market as a force driving the market (and this wallet service is predominantly accessed from the US).
 

Time series analysis and prediction

The application of genetic programming to the study of behavior and causation in cryptocurrency markets is not only an analytic artifact, but it is fundamentally aligned to the nature of the problem.   
Taleb and Douady \cite{Taleb_2013} explain that the natural selection of an evolutionary process is particularly antifragile, since a more volatile environment increases the survival rate of robust species and eliminates those whose superiority over other species is highly dependent on environmental parameters. In the context of cryptocurrencies, we could use temporal correlations in blockchain traffic to gauge the response of a given object (e.g. fees) to the volatility of an external stressor that affects it, but another approach is to simply study the response of market (as measured by a common risk metric, such as volatility) to the actual market behavior (with the consumption of services and information measured by HTTPs requests, including endogenous variables such as the activity at the customer service channels of the wallet and the exchange itself, mining pools, mining profitability feeds, and so on). The driving variables are be modeled using symbolic model ensambles, as in Figure 1. The nonlinearity in a source of stress is necessarily associated with fragility. This is why low quality coins fail --marketing activity is an environmental variable, while actual installed capacity and operational infrastructure (i.e bitcoin's) is a robustness contributor factor.