Financial engineering and the digital economy: The implementations of machine learning algorithms

The digital economy is quickly expanding, particularly in developing nations, as digital technologies are widely adopted. These technologies are revolutionizing many sectors, accelerating digitization throughout industries. The digital economy seeks to increase economic productivity and innovation b...

Full description

Saved in:
Bibliographic Details
Main Authors: Pingping Fu, Honghao Yang, Wenhao Qian, ELsiddig Idriss Mohamed, Wafa Ali J. Almohri, Huda M. Alshanbari
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016825004302
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The digital economy is quickly expanding, particularly in developing nations, as digital technologies are widely adopted. These technologies are revolutionizing many sectors, accelerating digitization throughout industries. The digital economy seeks to increase economic productivity and innovation by exploiting digital data, information, and communication technology. Within the area of digital currencies, bitcoin has developed as a significant subgroup. Its quick growth and adoption have had a profound impact on financial markets around the world. The purpose of this study is to forecast financial market trends by considering variables like bitcoin prices, coal pricing, hydroelectric power, and thermal energy. The timeframe of our study includes monthly data during the period from February 2016 to March 2024. The study utilizes comprehensive tools that integrate machine learning (ML) techniques with classical time series models. By applying such sophisticated tools, we aim to deliver forecasts that are both accurate and actionable, thereby empowering stakeholders to make informed decisions in increasingly digital and interconnected economy. The empirical results indicate that ANN outperforms other models, achieving the lowest RMSE (0.339) and MAE (0.271), making it the most accurate for predicting the Pakistan stock market. These findings highlight the potential of advanced ML models in financial forecasting.
ISSN:1110-0168