Forecasting Financial Market Volatility Using a Dynamic Topic Model

Morimoto, Takayuki; Kawasaki, Yoshinori

doi:10.1007/s10690-017-9228-z

Cited by 18 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial analysis of time series usually uses chart observation to compare intuitive data or discover the development rules in the series. This method is called descriptive time series analysis [4]. The ancient Egyptians found that the Nile flood law was based on this analysis method.…”

Section: ) Descriptive Time Series Analysismentioning

confidence: 99%

Financial Market Sequence Prediction Based on Image Processing

Liu

2024

IEEE Access

View full text Add to dashboard Cite

The rapid development of image and video processing technology has a significant impact on various industries. The analysis and forecast of the financial market income can not only provide investors with investment decisions, but also can correctly formulate various economic control policies for the government. The purpose of this study is to analyze and predict the financial market returns and various indexes based on deep learning CNN neural network algorithm in image processing technology. This study uses the time series method, using the convolution pooling process in CNN to effectively capture the local correlation characteristics of financial market data, then extract the important information hidden in the time series data, draw the trend curve of this information, and combine the features through image processing technology, finally realize the prediction of the financial market time series income index. The results show that in the deep learning algorithm of this study, the highest actual value of stock price after image processing is 3374, and the highest error value is 5.176%, which is nearly 20% less than other algorithms. When N1 = 1600, 3032 sliding windows are obtained, and the Euclidean norm of this point is 0.1586. The conclusion is that the deep learning algorithm of this study is effective and accurate for the prediction of financial market series. Image processing and data analysis technology provide effective methods and make important contributions to the research of financial field.

show abstract

Section: ) Descriptive Time Series Analysismentioning

confidence: 99%

Financial Market Sequence Prediction Based on Image Processing

Liu

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…They used ninety search terms related to the energy market and they contrasted them with the usual GARCH. (Morimoto & Kawasaki, 2017) modelled market volatility taking into account on line intraday news using HAR models, big data techniques and text mining techniques.…”

Section: Theory and Literature Reviewmentioning

confidence: 99%

The Google trends effect on the behavior of the exchange rate Mexican peso - US dollar

Bustamante

Valle

Ramírez

2018

CyA

View full text Add to dashboard Cite

<p>We show the advantage of using Google search engine trends to forecast the volatility of the shortterm (weekly) exchange rate between the Mexican peso and United States dollar. We perform a comparison of models in the literature that have used Google Trends to examine explanatory variables. Some of<br />the models are based on time series, whereas others are based on the similarity function, which captures the cognitive form of human reasoning. For example, an investor who needs to know the value that a variable will take in the future will take into account relevant, known, and available information, and weigh it to calculate the forecast. We conclude that taking into account the Google Trends variable helps explains partially the behaviour of volatility; and it is necessary to incorporate more aggregation levels. Moreover, to the best of our knowledge, literature on the subject of using Google Trends to explain relevant economic variables is relatively scarce.</p>

show abstract

“…While these models assume independence between topics, extensions to allow for direct correlation between topics such as Correlated Topic Models [9], or indirectly via grouped topic models such as Hierarchical Dirichlet Process (HDP) [10] and Group Latent Dirichlet Allocation (GLDA) [11], exist. Further, topic modelling tools addressing the transitional nature of information such as Dynamic Topic Models (DTM) [12] can be used to evaluate the evolution of latent topics over time [13][14][15]. Note that most of these methods constitute LDA or an extension of LDA.…”

Section: Introductionmentioning

confidence: 99%

Two-stage topic modelling of scientific publications: A case study of University of Nairobi, Kenya

Muchene¹,

Safari

2021

PLoS ONE

View full text Add to dashboard Cite

Unsupervised statistical analysis of unstructured data has gained wide acceptance especially in natural language processing and text mining domains. Topic modelling with Latent Dirichlet Allocation is one such statistical tool that has been successfully applied to synthesize collections of legal, biomedical documents and journalistic topics. We applied a novel two-stage topic modelling approach and illustrated the methodology with data from a collection of published abstracts from the University of Nairobi, Kenya. In the first stage, topic modelling with Latent Dirichlet Allocation was applied to derive the per-document topic probabilities. To more succinctly present the topics, in the second stage, hierarchical clustering with Hellinger distance was applied to derive the final clusters of topics. The analysis showed that dominant research themes in the university include: HIV and malaria research, research on agricultural and veterinary services as well as cross-cutting themes in humanities and social sciences. Further, the use of hierarchical clustering in the second stage reduces the discovered latent topics to clusters of homogeneous topics.

show abstract

Forecasting Financial Market Volatility Using a Dynamic Topic Model

Cited by 18 publications

References 31 publications

Financial Market Sequence Prediction Based on Image Processing

Financial Market Sequence Prediction Based on Image Processing

The Google trends effect on the behavior of the exchange rate Mexican peso - US dollar

Two-stage topic modelling of scientific publications: A case study of University of Nairobi, Kenya

Contact Info

Product

Resources

About