Candlestick pattern classification approaches take the hard work out of visually identifying these patterns. To highlight its capabilities, we propose a two-steps approach to recognize candlestick patterns automatically. The first step uses the Gramian Angular Field (GAF) to encode the time series as different types of images. The second step uses the Convolutional Neural Network (CNN) with the GAF to encode images to learn eight critical kinds of candlestick patterns.

The Candlestick is one of the most critical tools in financial transactions to help determine market sentiment. In this embodiment, the time series of the squall line data converted into a two-dimensional image, and the two-dimensional image is input to the convolutional neural network to identify the squall line pattern, so that a good identification effect can achieve.

In the past, program transactions were screened and identified by setting specific conditions. This product emulates the real trading scene of the trader, and through the direct operation of the image, the trader can more intuitively use the "disc feeling" to identify the powerful features, thereby adjusting the computer and effectively improving the model.