الفهرس 
Introduction and SummaryOnly 14 pages are availabe for public view
 |  | from | 140 |  |  |
| | | from | 140 | | |
Abstract
Summary
Data mining usually means the approaches and appliances to nugget the implicit, unknown, potential, and valuable knowledge. Therefore, it can be considered a knowledge discovery essential for solving problems in a specific domain. One of the most important problems in modern finance is finding efficient ways to summarize and visualize the stock market data to give individuals or institutions useful information about the market behavior for investment decisions. The enormous amount of valuable data generated by the stock market has attracted researchers to explore this problem domain using different methodologies. Potential significant benefits of solving these problems motivated extensive research for years. The research in data mining has gained a high attraction due to the importance of its applications and the increasing generation of information. The main objective of our study is to apply many models of data mining techniques and compare them to take the best model to help investors decide the best time for buying or selling stocks based on the knowledge extracted from the historical prices of proposed stocks. The process of decision-making will be based on data mining techniques. Therefore, in this thesis, we submitted some different methods, Linear Regression, Lasso Regression, Ridge Regression, Polynomial Regression, Huber Regression, Random Sample Consensus (RANSAC) Regression, ARIMA Models, Non-Linear Least Squares Curve Fitting using the Gaussian function, Convolutional Neural Network Long Short-Term Memory (CNN-LSTM), Long Short-Term Memory (LSTM) as an Artificial Recurrent Neural Network (RNN), Random Forest Regression, XGBoost Regression, and Support Vector Regression to compare them applied to the Egyptian stock market and found the best model to recommend to the investors. Based on the empirical results, it is found that the robust regression model has attained the best coefficient of determination score. Furthermore, MSE, RMSE, and R2 for all models have been compared.