Representing Price with Polar Coordinates for Angle-Based Trading Features

Summary

This article proposes representing a bar’s open and close prices as Cartesian coordinates, then converting them into polar coordinates: a radial distance and an angle. It explains how trigonometric transformations and derivatives can be calculated in MQL5, exported with historical price data, and used as inputs or prediction targets in a Python workflow. The motivation is to give price-angle features a defined mathematical construction and avoid undefined values encountered in an earlier approach.

The example labels whether the next observed close rises or falls and trains models to predict future radial distance and angle, then uses those predictions to form trading signals in an expert advisor. The author reports 88% accuracy on out-of-sample data. That figure is presented without enough detail here to assess the dataset, validation design, costs, or robustness, and the shown transformation may encode price level rather than an independent measure of price movement. The result is therefore an exploratory feature-engineering example, not evidence of live trading profitability.

Key ideas

• Open and close prices are treated as coordinates and transformed into radial distance and angle features.
• The article derives trigonometric features and their derivatives for export from MQL5 to Python.
• Separate models are used to predict future radial distance and angle, which inform a trading signal.
• The author reports 88% out-of-sample accuracy, but the excerpt does not give enough validation details to judge robustness or profitability.

Tags

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