Stock Price Prediction Based on Natural Language Processing1 (2022-05-06T00:00:00.000000Z)

TL;DR

The keywords augmentation model designed in this study is helpful to provide references for other variable expansion in financial time series forecasting and shows that, compared with seed keywords, the search indexes of extracted words have higher correlations with CSI 300 and can improve its forecasting performance.

Abstract

The keywords used in traditional stock price prediction are mainly based on literature and experience. This study designs a new text mining method for keywords augmentation based on natural language processing models including Bidirectional Encoder Representation from Transformers (BERT) and Neural Contextualized Representation for Chinese Language Understanding (NEZHA) natural language processing models. The BERT vectorization and the NEZHA keyword discrimination models extend the seed keywords from two dimensions of similarity and importance, respectively, thus constructing the keyword thesaurus for stock price prediction. Furthermore, the predictive ability of seed words and our generated words are compared by the LSTM model, taking the CSI 300 as an example. The result shows that, compared with seed keywords, the search indexes of extracted words have higher correlations with CSI 300 and can improve its forecasting performance. Therefore, the keywords augmentation model designed in this study is helpful to provide references for other variable expansion in financial time series forecasting.

Authors

Xiaobin Tang

1 papers

Nuo Lei

1 papers

Manru Dong

1 papers

TL;DR

Abstract

Authors

References43 items

LSH-aware multitype health data prediction with privacy preservation in edge environment

A long short‐term memory‐based model for greenhouse climate prediction

Big Data Business Actual Analysis: Stock Price Prediction Based on Time Series Model

Measuring Accuracy of Stock Price Prediction Using Machine Learning Based Classifiers

Stock Price Prediction using Bi-Directional LSTM based Sequence to Sequence Modeling and Multitask Learning

Stock Price Prediction Using CNN and LSTM-Based Deep Learning Models

Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models

Sentiment Analysis for Stock Price Prediction

A Time Series Analysis-Based Stock Price Prediction Using Machine Learning and Deep Learning Models

CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model

Incorporating BERT into Neural Machine Translation

Using Google Trends and Baidu Index to analyze the impacts of disaster events on company stock prices

NEZHA: Neural Contextualized Representation for Chinese Language Understanding

How to Fine-Tune BERT for Text Classification?

BERT with History Answer Embedding for Conversational Question Answering

Development of stock market trend prediction system using multiple regression

ModAugNet: A new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module

Predicting the direction of stock markets using optimized neural networks with Google Trends

Deep Contextualized Word Representations

Deep learning with long short-term memory networks for financial market predictions

Stock market one-day ahead movement prediction using disparate data sources

Stock Price Prediction Using the ARIMA Model

Quantifying Trading Behavior in Financial Markets Using Google Trends

Efficient Estimation of Word Representations in Vector Space

TextRank: Bringing Order into Text

Multiple Regression

Long Short-Term Memory

On the construction of effective vocabularies for information retrieval

EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK*

“A new method of stock index prediction based on sentiment analysis of ﬁnancial text,”

Research on the next-generation deep learning framework

“Research on the prediction of consumer conﬁdence index based on machine learning LSTM&US model,”

Stock Price Prediction Using Convolutional Neural Networks on a Multivariate Timeseries

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Research on fundamental quantitative investment driven by machine learning

Improving Language Understanding by Generative Pre-Training

Efficient Capital Markets: A Review of Theory and Empirical Work

Stock Market Prediction with Deep Learning: A Character-based Neural Language Model for Event-based Trading

Evolutionary Based ARIMA Models for Stock Price Forecasting

Jieba” Chinese Text Segmentation

Latent Dirichlet Allocation

Efficient Capital Markets : A Review of Theory and Empirical Work

Indexing by latent semantic analysis

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names