Predicting the daily index of the Tehran Stock Exchange using the selection of appropriate features for the Long Short-Term Memory neural network (LSTM)

Mohebi, Somayeh; Fadaeinejad, Mohammad Esmaeil; osoolian, mohammad; Hamidizadeh, Mohammad reza

Manuscript ID : FEJ-2206-3305 (R1) Visit : 219 Page: 231 - 251

Article Type: Original Research

Predicting the daily index of the Tehran Stock Exchange using the selection of appropriate features for the Long Short-Term Memory neural network (LSTM)

Subject Areas : Stock Exchange

Somayeh Mohebi ¹ ( Ph.D. Candidate of Financial Management, Faculty of Management and Accounting, Shahid Beheshti University, Tehran, Iran. )
Mohammad Esmaeil Fadaeinejad ² ( Associate Prof., Department of Financial Management and Insurance, Faculty of Management &amp; Accounting, Shahid Beheshti University, Tehran, Iran )
mohammad osoolian ³ ( Assistant Prof., Department of Financial Management and Insurance, Faculty of Management &amp; Accounting, Shahid Beheshti University, Tehran, Iran. )
Mohammad reza Hamidizadeh ⁴ ( Prof.. Department of Commercial Management. Faculty of Management and Accounting, Shahid Beheshti University, Tehran, Iran. )

Received: 2022-06-19 Accepted : 2022-09-12 Published : 2023-06-22

Keywords: "Stock Index Prediction". "Feature Selection", "Deep Learning", "Long Short-Term Memory",

Abstract :

The stock market index is one of the effective features in investment because it can well reflect the health status and macro change trend of a country’s economic development. Various features affect the stock index. The various combinations of these features create a wide state space. Hence, it is impractical to provide a data set containing all these combinations to train the stock index prediction model. in this research, an attempt has been made, after collecting a significant number of effective features on the index, to provide a method for selecting appropriate features for the stock index prediction model with aim of increasing prediction accuracy. For this purpose, the mRMR algorithm is used as the basic algorithm. Also, to select the appropriate model, a number of the most applicable artificial intelligence models for predicting the stock index were compared and according to the results, the LSTM network was selected to predict the stock index. The results of this study show that using the LSTM network and the proposed method in selecting features, with 8 selected features, high accuracy can be achieved in the daily prediction of the Tehran Stock Exchange Index. So that MPE is calculated to be about 2.66,

References:
_||_

The Distributional Changes of Financial Assets’ Return in Pre and Post COVID 19 Based on Power Law, Stretched Exponential Function and q-Gaussian Function
Print Date : 2024-08-15
Measuring the severity size and direction of fluctuations or exchange rate shocks in the money, capital and insurance markets
Print Date : 2022-09-23
Ranking of banks based on CAMELS indicators to predict financial distress by logistic regression and Data Envelopment Analysis
Print Date : 2023-06-22
Comparison of different machine learning models in stock market index forecasting
Print Date : 2023-09-23
Predicting stock returns at the company level: An application of linking asset pricing models and economic factors
Print Date : 2024-08-15
Financial risk evaluation of investment companies in Tehran Stock Exchange with fuzzy decision-making method D-CRITIC and EDAS based on a new score function
Print Date : 2023-09-23

Share To

Article Url

Predicting the daily index of the Tehran Stock Exchange using the selection of appropriate features for the Long Short-Term Memory neural network (LSTM)