[PDF] Hierarchical Multi-Scale Gaussian Transformer for Stock

Hierarchical Multi-Scale Gaussian Transformer for Stock Movement

Predicting the price movement of finance securi- ties like stocks is an important but challenging task due to the uncertainty of financial markets. In this.

Stock price prediction using BERT and GAN

18 juil. 2021 an ensemble of state-of-the-art methods for predicting stock prices. ... sion of BERT which is a pre-trained transformer model by Google.

Predicting Stock Closing Prices in Emerging Markets with

This research proposes a novel fintech machine learning method that uses Transformer neural networks for stock price predictions. Transformers are relatively 

Transformer-Based Capsule Network For Stock Movements Prediction

From our re- sults we also prove that the Transformer encoder is better than other models in the task of stock movements prediction. At the same time

Accurate Multivariate Stock Movement Prediction via Data-Axis

In this work we propose DTML (Data-axis. Transformer with Multi-Level contexts)

Accurate Multivariate Stock Movement Prediction via Data-Axis

18 août 2021 and c) utilizing a transformer encoder for learning inter-stock corre- ... stock movement prediction transformers

Accurate Multivariate Stock Movement Prediction via Data-Axis

18 août 2021 In this work we propose DTML (Data-axis. Transformer with Multi-Level contexts)

Multi-Transformer: A New Neural Network-Based Architecture for

28 juil. 2021 Stock volatility forecasts play a key role in the estimation of equity risk and ... order to predict cryptocurrencies volatility.

Accurate Multivariate Stock Movement Prediction via Data-Axis

To predict the future values of stock prices Data-axis Transformer with Multi-Level contexts ... To learn the stock correlations by a transformer.

NumHTML: Numeric-Oriented Hierarchical Transformer Model for

cal transformer model (NumHTML) to predict stock returns earnings calls data for stock movement prediction. The start-.

Hierarchical Multi-Scale Gaussian Transformer for Stock

In this paper we propose a new Transformer-based method for stock movement prediction The primary highlight of the proposed model is the capability of capturing long-term short-term as well as hierarchical dependencies of ?nancial time series For these aims we propose several enhancements for the Transformer-based model: (1) Multi-Scale

Can transformer predict the stock market index?

Zhou et al. (2021) proposed an improved Transformer model called Informer for long-sequence time series forecasting. Based on similar ideas, this paper considers Transformer to predict the stock market index. As far as we know, it is an innovative work to evaluate the performance of Transformer on the stock market prediction. 3. Background

Does transformer outperform other deep learning models in stock market prediction?

Compared with the traditional deep learning models, such as CNN, RNN, and LSTM, Transformer exhibits higher prediction accuracy and better net worth curves in all experiments. These results demonstrate that Transformer outperforms other existing models in stock market prediction.

Can transformer model be used for stock price prediction at DSE?

The transformer model has been widely leveraged for natural language processing and computer vision tasks, but, to the best of our knowledge, has never been used for stock price prediction task at DSE.

Can a transformer model predict a linear trend?

When only using the IBM stock history even a transformer model is merely capable of predicting the linear trend of a stock’s development. Concluding that the historical price and volume data of a stock does only contain enough explanatory value for a linear trend prediction.