2006
DOI: 10.1007/s10489-006-0001-7
|View full text |Cite
|
Sign up to set email alerts
|

Stock market prediction with multiple classifiers

Abstract: Stock market prediction is attractive and challenging. According to the efficient market hypothesis, stock prices should follow a random walk pattern and thus should not be predictable with more than about 50 percent accuracy. In this paper, we investigated the predictability of the Dow Jones Industrial Average index to show that not all periods are equally random. We used the Hurst exponent to select a period with great predictability. Parameters for generating training patterns were determined heuristically … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
127
1
4

Year Published

2010
2010
2022
2022

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 201 publications
(132 citation statements)
references
References 30 publications
(21 reference statements)
0
127
1
4
Order By: Relevance
“…We do not have proofs that the model presented in this paper for trading in sports betting markets would also have good performance for predicting price movements in financial markets. In addition, could also be interesting to apply techniques of financial markets to sports betting markets [31].…”
Section: Discussion and Future Workmentioning
confidence: 99%
See 1 more Smart Citation
“…We do not have proofs that the model presented in this paper for trading in sports betting markets would also have good performance for predicting price movements in financial markets. In addition, could also be interesting to apply techniques of financial markets to sports betting markets [31].…”
Section: Discussion and Future Workmentioning
confidence: 99%
“…Other techniques similar to some of the used for stock markets prediction [31] such as neural networks, support vector machines, quantitative matrix's, etc., could also be used, but this work is not focused on finding the best-performance technique for trading in sports betting markets.…”
Section: Introductionmentioning
confidence: 99%
“…Time series analysis and prediction is an important task in all fields of science for applications like financial forecasting, weather forecasting, electricity power demand forecasting, process monitoring and control, research, medical sciences, etc., Artificial neural networks are widely used for solving pattern prediction problems [1][2][3][4][5][6][7][8][9]. Different types of neural networks exist and every neural network has its own benefits and limitations.…”
Section: Introductionmentioning
confidence: 99%
“…Em seu artigo, ele comenta vários trabalhos de predição para mercado de ações, especialmente alguns da década de 60 baseados em 'Random Walk Theory' (teoria do passeio aleatório) e 'Efficient Market Hypothesis' -Hipótese do Mercado Eficiente (EMH, do inglês) . A EMH afirma que a valorização do mercado financeiro incorpora quaisquer novas notícias e informações [9,10], ou seja, os preços do mercado de ações são, em grande parte, impulsionados por novas informações e não por preços do presente e do passado. Como uma nova notícia ou informação é algo imprevisível, de acordo com essa teoria, os preços seguiriam um padrão de passeio randômico e não poderiam ser preditos com precisão superior a 50%.…”
Section: Contextualizaçãounclassified
“…Entretanto, essa teoria é desafiada por vários pesquisadores que, baseados nas perspectivas da teoria de finança socioeconômica e enfatizando a importância de fatores comportamentais e emocionais, incluindo o humor social [11], a criticam e afirmam que os preços nem sempre seguem um passeio aleatório [9], e podem, até certo ponto, serem preditos. Pesquisas recentes sugerem que apesar de a notícia ser algo imprevisível, muitos indicadores precoces podem ser extraídos da mídia social online para estimar mudanças em vários indicadores econômicos e comerciais, e que esse também pode ser o caso do mercado de ações [7].…”
Section: Contextualizaçãounclassified