The Impact of Big Data Techniques on Predicting Stock Prices: Evidence from Jordan

Abstract

The purpose of this study is to demonstrate the impact of big data analytics techniques on predicting stock prices in industrial companies listed on the Amman Stock Exchange (ASE) from the perspective of employees in Jordanian financial intermediation firms. To achieve the goal of this research, two approaches were used. The first approach is an analytical descriptive approach that collects primary data through a survey that measures the elements of the independent variable related to big data analytics techniques (Volume, Velocity, Variety, and Veracity). A second approach is an applied approach that measures the dependent variable of stock price prediction using financial statements from industrial companies listed on the ASE from 2015 to 2021. Multiple regression tests were used to test the hypotheses and extract the results, which demonstrated that big data technologies play an important role in providing appropriate and reliable information to predict the prices of stock exchange traded shares. The variable "veracity" ranked first in the power of influence in predicting share prices, while the variable "volume" ranked last. These findings suggest that ASE dealers prioritize the credibility of data received from companies over the rest of the information resulting from big data analyses to predict stock prices traded on the stock exchange.