Testing Naive and Adaptive Candlestick Direction Forecasts

Summary

The article tests three simple forecasts for the next candle: repeat the previous candle’s direction, predict the opposite direction, or switch between those rules after a forecast error. Candle direction is defined by whether its close is above, below, or equal to its open. The proposed expert advisor opens a position at a new bar based on the preceding candle, then closes earlier positions as each bar advances.

Backtests cover multiple forex pairs and chart intervals, comparing net profit and the share of profitable trades. The repeat-direction rule performs poorly across the reported tests; the reverse rule is somewhat better in some cases but inconsistent. The adaptive switching rule also fails to improve results reliably. These findings illustrate the weakness of using candle direction alone as a forecast, but the tests are limited to the stated instruments, history, and setup. The article does not establish whether these rules could work with other execution assumptions, risk controls, or additional signals.

Key ideas

• The three forecasts either repeat the previous candle’s direction, reverse it, or switch rules after a mistake.
• Candle direction is determined by the sign of the difference between closing and opening prices.
• The expert advisor tests signals at each new bar and evaluates net profit and winning-trade percentage.
• The reported tests show weak results for all three approaches, with no reliable benefit from adaptive switching.
• The conclusions are limited to the tested pairs, intervals, history, and trading setup.

Tags

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