International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 184 - Number 43 |
Year of Publication: 2023 |
Authors: Ismail M. Hagag |
![]() |
Ismail M. Hagag . Assessing Machine Learning Linear Models to Predict Egyptian Stock Market Prices. International Journal of Computer Applications. 184, 43 ( Jan 2023), 33-43. DOI=10.5120/ijca2023922543
Despite significantly related difficulties, the search for models to predict the prices of financial markets remains a highly researched subject. Financial time series are challenging to forecast because of the non-linear, chaotic, and dynamic nature of the prices of financial assets. Given their capacity to recognize complex patterns in various applications, machine learning models are among the most researched of the most recent techniques. The objective of this research is to identify the most effective method (among the selected methods) for forecasting stock markets by evaluating the accuracy of these models using the EGX100 market indicator. By applying nine different algorithms on the EGX100 daily prices we, namely Decision Tree (DT), Support Vector Machine (SVM), extreme Gradient Boost (XGBoost), AdaBoost, Multiple layer perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), Logistic Regression (LR), and K Nearest Neighbour (KNN). we have found that Linear regression is by far the best machine-learning algorithm for this type of problem. This result is reached through the usage of four different metrics after changing the problem into a classification problem.