A Hybrid Stock Price Prediction Model Based on PRE and Deep Neural Network

A novel pyramid temporal causal network for weather prediction

In the field of deep learning, sequence prediction methods have been proposed to address the weather prediction issue by using discrete weather data over a period of time to predict future weather. However, extracting and utilizing feature information of different time scales from historical meteorological data for weather prediction remains a challenge. In this paper, we propose a novel model called the Pyramid Temporal Causal Network (PTCN), which consists of a stack of multiple causal dilated blocks that can utilize multi-scale temporal features. By collecting features from all the causal dilated blocks, PTCN can utilize feature information of different time scales. We evaluate PTCN on the Weather Forecasting Dataset 2018 (WFD2018) and show that it benefits from multi-scale features. Additionally, we propose a multivariate loss function (MVLoss) for multivariate prediction. The MVLoss is able to accurately fit small variance variables, unlike the mean square error (MSE) loss function. Experiments on multiple prediction tasks demonstrate that the proposed MVLoss not only significantly improves the prediction accuracy of small variance variables, but also improves the average prediction accuracy of the model.

Cryptocurrency Price Prediction with Convolutional Neural Network and Stacked Gated Recurrent Unit

Virtual currencies have been declared as one of the financial assets that are widely recognized as exchange currencies. The cryptocurrency trades caught the attention of investors as cryptocurrencies can be considered as highly profitable investments. To optimize the profit of the cryptocurrency investments, accurate price prediction is essential. In view of the fact that the price prediction is a time series task, a hybrid deep learning model is proposed to predict the future price of the cryptocurrency. The hybrid model integrates a 1-dimensional convolutional neural network and stacked gated recurrent unit (1DCNN-GRU). Given the cryptocurrency price data over the time, the 1-dimensional convolutional neural network encodes the data into a high-level discriminative representation. Subsequently, the stacked gated recurrent unit captures the long-range dependencies of the representation. The proposed hybrid model was evaluated on three different cryptocurrency datasets, namely Bitcoin, Ethereum, and Ripple. Experimental results demonstrated that the proposed 1DCNN-GRU model outperformed the existing methods with the lowest RMSE values of 43.933 on the Bitcoin dataset, 3.511 on the Ethereum dataset, and 0.00128 on the Ripple dataset.