Scholarlink

This study aims to enhance the prediction accuracy of the daily ASE’s weighted price index of the banking sector (SCB) through the application of a nonlinear spectral model known as maximum overlapping discrete wavelet transform (MODWT). The model incorporates five mathematical functions: Haar, Daubechies (Db4), least square (LA8), best localization (BL14), and Coiflet (C6). Employing a genetic fuzzy system based on Thrift’s methodology (GFS.Thrift), the study leverages a dataset provided by the Amman Stock Exchange (ASE) consisting of 4,423 observations spanning from January 2, 2006, to January 7, 2024. The adaptive GFS.THRIFT model undergoes training with 90% of the dataset, while the remaining 10% is reserved for testing its predictive capabilities. The selection of input variables, including standardized gross domestic product (SGDP) and inflation (SI), is conducted through multiple regressions and multicollinearity tests. Findings from the study reveal a negative relationship between SGDP and SCB, while a positive association is observed between SI and SCB. Notably, the proposed model (GFS. Thrift + C6) demonstrates superior performance compared to other existing models, including the original GFS.Thrift model.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Innovative Approach to Forecasting Jordanian Commercial Bank Stock Market Using a Hybrid Genetic Algorithm-Fintech Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jamil J. Jaber,
  • Younis Ahmed Ghulam,
  • Anwar Al-Gasaymeh,
  • Amro S. Alamaren,
  • Mheel AL-Smaihyeen

摘要

This study aims to enhance the prediction accuracy of the daily ASE’s weighted price index of the banking sector (SCB) through the application of a nonlinear spectral model known as maximum overlapping discrete wavelet transform (MODWT). The model incorporates five mathematical functions: Haar, Daubechies (Db4), least square (LA8), best localization (BL14), and Coiflet (C6). Employing a genetic fuzzy system based on Thrift’s methodology (GFS.Thrift), the study leverages a dataset provided by the Amman Stock Exchange (ASE) consisting of 4,423 observations spanning from January 2, 2006, to January 7, 2024. The adaptive GFS.THRIFT model undergoes training with 90% of the dataset, while the remaining 10% is reserved for testing its predictive capabilities. The selection of input variables, including standardized gross domestic product (SGDP) and inflation (SI), is conducted through multiple regressions and multicollinearity tests. Findings from the study reveal a negative relationship between SGDP and SCB, while a positive association is observed between SI and SCB. Notably, the proposed model (GFS. Thrift + C6) demonstrates superior performance compared to other existing models, including the original GFS.Thrift model.