Testing Lunar and Solar Cycle Features for Currency Prediction

Summary

The article proposes turning lunar and solar timing into features for a currency forecasting model. It describes calculating phase angles from fixed cycle lengths and currency-specific reference dates, encoding phases with sine and cosine harmonics, and combining those signals with hand-assigned currency traits such as risk appetite and commodity sensitivity. Lagged phase and market features are also included, and the model is framed as a classifier for the direction or size of future moves rather than an exact price forecast.

The document claims a test on 15 years of market data and presents the idea as a research hypothesis, but the supplied excerpt omits key details of the validation and reported results. Its example effect calculation includes a random choice at critical lunar phases, while currency traits and phase impacts are asserted rather than empirically established. The method therefore needs reproducible testing, controls for data mining and a trading rule that accounts for costs before it can support a trading conclusion.

Key ideas

• Lunar and solar cycle positions are converted into phase angles using fixed astronomical periods and currency reference dates.
• Sine and cosine terms encode the phase and selected harmonics as model features.
• The proposed currency-pair effect combines phase rules with differences in assigned currency characteristics.
• Lagged astronomical and price variables extend the feature set beyond the current cycle state.
• The excerpt does not provide enough validation detail to establish predictive value or profitability.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.