Suppose investors want to directly predict the future transaction price or ups and downs. In that case, the fatal assumption is that the training data set is consistent with the data distribution that has not occurred in the future. However, the natural world will not let us know whether the subsequent data distribution will change. Because of this, even if researchers add a moving window to the training process, it is inevitable that "machine learning obstacles-prediction delay" will occur. Our method can avoid "machine learning obstacles-prediction delay", We also propose auto trading by deep reinforcement learning. Our new article has the following contributions: 1. Our first contribution is not to make future predictions but to focus on the current "candlesticks pattern detection", such as Engulfing Pattern, Morning Star,.... 2. Our second contribution focuses on detecting trading entry and exit signals combined with related investment strategies.

The following result is the output of my deep learning model. Only the last candlestick is the predicted result.For research purposes only. This forecast is published after today's market is open and the stock's open price is included in the model. Today's day high, day low and close prices are predicted. This forecast is published after market close.

A wide variety of deep reinforcement learning (DRL) models have recently been proposed to learn profitable investment strategies. The rules learned by these models outperform the previous strategies specially in high frequency trading environments. However, it is shown that the quality of the extracted features from a long-term sequence of raw prices of the instruments greatly affects the performance of the trading rules learned by these models. Employing a neural encoder-decoder structure to extract informative features from complex input time-series has proved very effective in other popular tasks like neural machine translation and video captioning in which the models face a similar problem. The encoder-decoder framework extracts highly informative features from a long sequence of prices along with learning how to generate outputs based on the extracted features. In this paper, a novel end-to-end model based on the neural encoder-decoder framework combined with DRL is proposed to learn single instrument trading strategies from a long sequence of raw prices of the instrument. The proposed model consists of an encoder which is a neural structure responsible for learning informative features from the input sequence, and a decoder which is a DRL model responsible for learning profitable strategies based on the features extracted by the encoder. The parameters of the encoder and the decoder structures are learned jointly, which enables the encoder to extract features fitted to the task of the decoder DRL. In addition, the effects of different structures for the encoder and various forms of the input sequences on the performance of the learned strategies are investigated. Experimental results showed that the proposed model outperforms other state-of-the-art models in highly dynamic environments.

Candlesticks are graphical representations of price movements for a given period. 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.

The python package pastalog has a node.js Once you have a server running, you can start logging your progress. Go to localhost:8120 and view your logs updating in real time. Note: If you want to compare models across batch sizes, a good approach is to pass to step the fractional number of times the model has seen the data (number of epochs). In that case, you will have a fairer comparison between a model with batchsize 50 and another with batchsize 100, for example.