Abstract
Stock price forecasting is one of the most challenging activities for traders and financial analysts due to the high volatility of stock market data. Investing in the stock market is often associated with a significant risk, hence the need for a forecasting model to minimize it. To maximize profit, investors must anticipate upward trends to place sales orders at the highest possible price. This article aims to present a new model for uptrend detecting for a given horizon. Our proposed model consists of successive phases: the first phase is for selecting stock market that have returns normally distributed. Note that the returns in our case reflect the evolution of prices average in a given period compared to the current price. Then a filtration that aims to keep only the stock price that have the average ratio over standard deviation as high as possible. Subsequently, we create our portfolio using selected stock market. In the next phase, we will build classes by comparing returns to a given limit. The next step is for training and testing two classifier: LSTM classifier and nearest neighbor classifier. The last phase is to cross the results provided by the two models and decide on the value to be predicted according to a decision rule. Experience shows that our proposed model gives very promising results and its accuracy to predict uptrend is high.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Box, G.E.P., Jenkins, G.M., Reinsel, G.C.: Time Series Analysis Forecasting and Control. Wiley, New York (2008)
Olson, D.L., Delen, D.: Advanced Data Mining Techniques. Springer, Heidelberg (2008)
Patel, J., Shah, S., Thakkar, P., Kotecha, K.: Predicting stock market index using fusion of machine learning techniques. Expert Syst. Appl. 42, 2162–2172 (2015)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Bao, W., Yue, J., Rao, Y.: A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLOS ONE 12 (2017). https://doi.org/10.1371/journal.pone.0180944
Vargas, M.R., de Lima, B.S., Evsukoff, A.G.: Deep learning for stock market prediction from financial news articles. In: 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), pp. 60–65. IEEE (2017)
Kim, H.Y., Won, C.H.: Forecasting the volatility of stock price index: a hybrid model integrating LSTM with multiple GARCH-type models. Expert Syst. Appl. 103, 25–37 (2018)
Abe, M., Nakayama, H.: Deep learning for forecasting stock returns in the cross-section. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) Advances in Knowledge Discovery and Data Mining, pp. 273–284. Springer International Publishing, Cham (2018)
Yan, H., Ouyang, H.: Financial time series prediction based on deep learning. Wireless Pers. Commun. 102, 683–700 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Touzani, Y., Douzi, K., Khoukhi, F. (2019). Stock Price Forecasting: Improved Long Short Term Memory Model for Uptrend Detecting. In: Khoukhi, F., Bahaj, M., Ezziyyani, M. (eds) Smart Data and Computational Intelligence. AIT2S 2018. Lecture Notes in Networks and Systems, vol 66. Springer, Cham. https://doi.org/10.1007/978-3-030-11914-0_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-11914-0_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-11913-3
Online ISBN: 978-3-030-11914-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)