Research on Support Vector Regression in the Stock Market Forecasting

Chun, Cai; Ma, Qingwei; Lv, Shuqiang

doi:10.1007/978-3-642-28655-1_96

Cited by 7 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the election to that ɑ * , the [5] = − Fig 10: The graph above shows the comparison between the actual value and predicted value for AAPL stock. The above graph is for the time span of 35 days for both actual and predicted price.…”

Section: Construct the Function Regression Estimatesmentioning

confidence: 99%

Stock Prediction and Simulation of Trade Using Support Vector Regression

.¹

2018

IJRET

View full text Add to dashboard Cite

Up's and Down's in share market are always unpredictable. Commercial banks offer their customers market predictions based on the sentiment and market news of the given day. These predictions are relevant for a short period of time. Commercial banks cater to a large demography hence they have to limit their prediction services. Investment banks have used predictive models which use past market data to predict stock prices and market indexes. Common people cannot afford the services provided by the investment bank. Candlestick is widely used in the trading community for analysis. But candlestick chart looks different for various time frames and they make it difficult to manage risks. The proposed system aims at helping traders make sound financial decisions. It simulates trading thereby helping new users understand the application.It will be of assistance to beginners so that they can learn how to trade without losing any capital. The system uses machine learning techniques and also lets the user view sentiment about the stock in real time. Both mathematical predictions and sentiments are used as parameters for making a financial decision. The proposed system is able to achieve prediction accuracy of up to 95%[1].

show abstract

Section: Construct the Function Regression Estimatesmentioning

confidence: 99%

Stock Prediction and Simulation of Trade Using Support Vector Regression

.¹

2018

IJRET

View full text Add to dashboard Cite

show abstract

“…Nevertheless, in support vector training process, the calculation of sample product will become very complicated. Kernel function converts the nonlinear separable data samples to linearly separable in a higher dimensional space, which avoids a huge amount of math problems and makes it easier for data mining . The calculation of the kernel function is to carry out the input space, and the computational complexity and the feature space's dimension depends on the number of the input space.…”

Section: Related Workmentioning

confidence: 99%

PM_2.5 forecasting with hybrid LSE model‐based approach

Chen

Deng

et al. 2016

Softw Pract Exp

View full text Add to dashboard Cite

SUMMARYPM 2:5 time series have the features of non-stationary and nonlinear. Existing forecasting methods for PM 2:5 cannot achieve high accuracy for they have ignored the potential characteristics of PM 2:5 time series. Aiming at this problem, a hybrid approach using local mean decomposition and Support Vector Regression (SVR)-Elman (LSE) is firstly proposed in this paper to analyse 5 days ahead PM 2:5 concentrations for forecasting in Wuhan, China: (1) the meaningful PF1-PF5 components are extracted from original PM 2:5 time series by local mean decomposition; (2) the first high-frequency product function is managed by using the SVR model, such that the relationship between PM 2:5 and other air quality data can be revealed accurately; (3) the other components are trained by Elman model with the sliding window method. Experimental results show that, compared with multiple linear regression, autoregressive integrated moving average, BP neural network, and SVR models, the proposed hybrid LSE model-based approach exhibits the best performance in terms of R 2 , MAE, MAPE, RMSE, while it is applied for forecasting in real datasets.

show abstract

“…In most of the papers that use regression analysis adjusted coefficient of determination is low, indicating a low interdependency of factors. According to Cai, Ma, and Lv (2012), the stock market, especially emerging markets, has high noise, nonlinearity and uncertainty characteristics, so traditional neural network forecasting method cannot deal with these problems. In small emerging markets, where the number of annual transactions is too small and where the data are unbalanced, the performance of DT models is not satisfactory (learning from unbalanced datasets presents a convoluted problem in which traditional learning algorithms may perform poorly, Cieslak & Chawla, 2008).…”

Section: Introductionmentioning

confidence: 99%

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Kašćelan¹,

Kašćelan²,

Jovanovic³

2014

Intelligent Automation & Soft Computing

View full text Add to dashboard Cite

In this study we developed a support vector machine (SVM) rule extraction method for discovering the effects of the features of investors and stock and corporate performance on stock trading preferences. We used this system to combine strengths of two approaches: SVM as an accurate classifier and a decision tree (DT) as a generator of interpretable models. The method is applied to Montenegro data in order to generate interpretable rules for stock market decision-makers. The results showed that this method, in terms of accuracy and interdependency of factors, outperformed the methods for detecting stock trading preferences from previous studies.

show abstract

Research on Support Vector Regression in the Stock Market Forecasting

Cited by 7 publications

References 0 publications

Stock Prediction and Simulation of Trade Using Support Vector Regression

Stock Prediction and Simulation of Trade Using Support Vector Regression

PM_2.5 forecasting with hybrid LSE model‐based approach

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Contact Info

Product

Resources

About

Research on Support Vector Regression in the Stock Market Forecasting

Cited by 7 publications

References 0 publications

Stock Prediction and Simulation of Trade Using Support Vector Regression

Stock Prediction and Simulation of Trade Using Support Vector Regression

PM2.5 forecasting with hybrid LSE model‐based approach

Hybrid support vector machine rule extraction method for discovering the preferences of stock market investors: Evidence from Montenegro

Contact Info

Product

Resources

About

PM_2.5 forecasting with hybrid LSE model‐based approach