An Improved Hybrid Algorithm Based on PSO and BP for Stock Price Forecasting

Gao, Yuelin

doi:10.2174/1874110x01509012565

Cited by 9 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They proposed a hybrid BP neural network combining adaptive particle swarm optimization algorithm (HBP-PSO) to predict the stock price of "Zhong Guo Yi Yao" (600056). The results support that the trend prediction accuracy of HBP-PSO is better than that of the simple neural network [6]. Using this criterion can ensure the prediction accuracy of the up and down signals of stock price to reduce the possibility of trading errors.…”

Section: Introductionsupporting

confidence: 61%

“…However, the second way does not yet work very well. One important reason is that different periods of a stock market, for example, rising period and falling period, have different inherent laws and scholars usually use a single neural networks model and the same set of parameters to deal with the different periods [5,6]. Another reason, the most difficult problem, is the effect of unexpected news, which could hardly be predicted.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Bimodel Algorithm with Data-Divider to Predict Stock Index

Wang

Yong-jie

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

There is not yet reliable software for stock prediction, because most experts of this area have been trying to predict an exact stock index. Considering that the fluctuation of a stock index usually is no more than 1% in a day, the error between the forecasted and the actual values should be no more than 0.5%. It is too difficult to realize. However, forecasting whether a stock index will rise or fall does not need to be so exact a numerical value. A few scholars noted the fact, but their systems do not yet work very well because different periods of a stock have different inherent laws. So, we should not depend on a single model or a set of parameters to solve the problem. In this paper, we developed a data-divider to divide a set of historical stock data into two parts according to rising period and falling period, training, respectively, two neural networks optimized by a GA. Above all, the data-divider enables us to avoid the most difficult problem, the effect of unexpected news, which could hardly be predicted. Experiments show that the accuracy of our method increases 20% compared to those of traditional methods.

show abstract

Section: Introductionsupporting

confidence: 61%

Section: Introductionmentioning

confidence: 99%

A Bimodel Algorithm with Data-Divider to Predict Stock Index

Wang

Yong-jie

2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…For the prediction, an update state method has been exploited to forecast time stages one after another and renovate the network state at every forecast. Furthermore, to prove the significance of the proposed model, the model is applied to three different datasets and benchmarked with three popular stock price forecasting methods Sun's model [21], Roondiwala's model [22], Basak's model [23]. Dataset #I is elected from the Standard and Poor's 500 Index; dataset #II comes from China Min-sheng Bank (CMSB), and dataset #III comes from Dow Jones Industrial Average [17].…”

Section: Experiments and Comparisonsmentioning

confidence: 99%

Forecasting Closing Price of Stock Market Using LSTM Network: An Analysis from the Perspective of Dhaka Stock Exchange

Kabir

Lima

Mridha

et al. 2021

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

As an essential ingredient of the financial market, the stock exchange has been involved by several researchers. Specific commercial prognostication is of magnificent possible engagement to both private and organizational investors. How to perceive the stock market trend and forecast the stock price is a dilemma many researchers investigate. In earlier studies, the prognostication techniques essentially concentrate on statistical principles and conventional neural network architectures that are comparatively familiar in contemporary times. In this study, Long Short Term Memory (LSTM) based novel architecture of forecasting stock closing price is investigated under the perspective of Dhaka stock exchange data. As the LSTM architecture has a long-term memory function, it performs the correct commercial timeseries prognostication. The performance of the proposed architecture is measured using MAE, RMSE, and MAPE evaluation matrixes. Our experiments show how MAE, RMSE, and MAPE scores significantly decrease after using the updated gate to train an LSTM network.

show abstract

“…Although trading on the foreign exchange instead of the stock exchange, the authors note that their system has shown to be profitable in testing. Sun and Gao [20] used PSO to optimize the weights on a neural network that predicted the prices of securities on an exchange. The authors note that their system was able to predict the price with an error rate of around 30% when compared to the actual prices.…”

Section: Market Timingmentioning

confidence: 99%