A Comparative Study on Market Index Prediction: Long Short- Term Memory (LSTM) vs. Decision Tree Model

Authors

Afrah Al-Bossly, Department of Mathematics, College of Science and Humanities in Al-Kharj, Prince Sattam Bin Abdulaziz University, Al- Kharj, 11942, Saudi ArabiaFollow
Manahill I. A. Anja, Computer Sciences Program, Department of Mathematics, Turabah University College, Taif University, P.O. Box 11099, Taif 21944, Saudi ArabiaFollow
Abdelgalal O. I. Abaker, Applied College, Khamis Mushait, King Khalid University, Abha, Saudi ArabiaFollow
Hago E. M. Ali, Department of Business Administration, Faculty of Science and Humanity Studies. Sulail, Prince Sattam bin Adalaziz University, Saudi ArabiaFollow
Salem Alkhalaf, Department of Computer, College of Science and Arts in Ar Rass, Qassim University, Ar Rass, Saudi ArabiaFollow

Author Country (or Countries)

Saudi Arabia

Abstract

The main objective of this article is to develop a linear exponential function risks in Saudi banks (LINEXLF) to estimate the shape parameter, reliability, and hazard rate functions of the Pareto distribution based on Type II Censored Data. By weighting LINEX loss function to produce a modified loss function called weighted linear exponential (WLINEXLF) loss function. We then use WLINEXLF to derive the shape parameter, reliability, and hazard rate functions of the Pareto distribution. Furthermore, to examine the performance of the proposed method WLINEXLF we conduct a Monte Carlo simulation. The comparison is between the proposed method and other methods including maximum likelihood estimation (MLE) and Bayesian estimation under the squared error loss function. The results of the simulation show that the proposed method WLINEXLF in this article has the best performance in estimating shape parameter, reliability, and hazard rate functions, according to the smallest values of mean squared error (MSE). This result means that the proposed method can be applied in real data in banking industrial sectors. This paper aims to use the modified loss function to estimate the shape parameter, reliability 𝑅(𝑡), and hazard rate functions h(𝑡) in Saudi banks of the Pareto distribution based on Type II Censored Data.

Digital Object Identifier (DOI)

http://dx.doi.org/10.18576/jsap/12S118

Recommended Citation

Al-Bossly, Afrah; I. A. Anja, Manahill; O. I. Abaker, Abdelgalal; E. M. Ali, Hago; and Alkhalaf, Salem (2023) "A Comparative Study on Market Index Prediction: Long Short- Term Memory (LSTM) vs. Decision Tree Model," Journal of Statistics Applications & Probability: Vol. 12: Iss. 4, Article 18.
DOI: http://dx.doi.org/10.18576/jsap/12S118
Available at: https://digitalcommons.aaru.edu.jo/jsap/vol12/iss4/18