Testing Astrological Data as Predictors of EUR/USD Prices

Summary

The article investigates whether planetary positions, lunar phases, solar activity, and planetary aspects can help forecast EUR/USD movements. It describes collecting daily astronomical data, aligning it with market history, and applying correlation analysis alongside regression and classification models. The stated results are weak: the regression explains little of future prices, lagged price information ranks ahead of planetary variables, and direction classification is only slightly above chance.

The author concludes that the tested astronomical inputs did not provide useful forecasting power and acknowledges that the analysis does not test every Gann-related feature. The conclusion should be read within the study's design: the excerpt describes a particular data range, feature construction, and modeling approach, and offers no evidence that alternative specifications would produce the same outcome. It nonetheless illustrates a quantitative way to evaluate an unconventional market hypothesis and report negative findings rather than relying on anecdotal correlations.

Key ideas

• The study combines astronomical observations with EUR/USD history to test proposed links between celestial cycles and market prices.
• It examines correlations and uses regression and classification to assess forecasting value.
• The reported regression performance is weak, with prior price information more important than planetary positions.
• The reported direction classifier performs only marginally better than chance.
• The findings apply to the tested features and modeling setup, while other Gann-derived inputs remain untested.

Tags

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