Explainable Deep Convolutional Candlestick Learner
This work addresses interpretability for traders using AI in financial markets, but it is incremental as it applies existing adversarial attack methods to a specific domain.
The paper tackles the problem of interpreting deep convolutional neural networks used for candlestick pattern recognition by introducing a framework that explains model reasoning using local search adversarial attacks, showing the model perceives patterns similarly to human traders.
Candlesticks are graphical representations of price movements for a given period. The traders can discovery the trend of the asset by looking at the candlestick patterns. Although deep convolutional neural networks have achieved great success for recognizing the candlestick patterns, their reasoning hides inside a black box. The traders cannot make sure what the model has learned. In this contribution, we provide a framework which is to explain the reasoning of the learned model determining the specific candlestick patterns of time series. Based on the local search adversarial attacks, we show that the learned model perceives the pattern of the candlesticks in a way similar to the human trader.