Forecasting of telecommunication stock prices using machine learning algorithms

Not available

Bibliographic Details
Main Author: Fong, Lee Ling
Other Authors: Nor Azizah Ali, supervisor
Format: Master's thesis
Language:English
Published: Universiti Teknologi Malaysia 2025
Subjects:
Online Access:https://utmik.utm.my/handle/123456789/40419
Abstract Abstract here
_version_ 1854975039146819584
author Fong, Lee Ling
author2 Nor Azizah Ali, supervisor
author_facet Nor Azizah Ali, supervisor
Fong, Lee Ling
author_sort Fong, Lee Ling
description Not available
format Master's thesis
id utm-123456789-40419
institution Universiti Teknologi Malaysia
language English
publishDate 2025
publisher Universiti Teknologi Malaysia
record_format dspace
record_pdf Abstract
spelling utm-123456789-404192025-08-20T15:36:19Z Forecasting of telecommunication stock prices using machine learning algorithms Fong, Lee Ling Nor Azizah Ali, supervisor Computing Not available Forecasting is a process that produces accurate predictions of the future course of trends using past data as inputs. The stock exchanges are marketplaces where stockbrokers and traders may purchase and sell securities including stocks, bonds, and other financial instruments. Forecasting of stock prices is very important in analyst the trend of stock prices since forecasting of stock market seeks to foresee future variations in a commercial exchange's stock value. However, forecasting of stock prices still one of the most challenging tasks due to obvious various variables involved in stock forecasting, which lead to the stock market highly uncertainty. In order to forecast the stock prices, machine learning algorithms can be introduced to forecast the trend of stock value. There are numerous methods have been used by other researchers to implement the forecasting of stock prices previously. The purpose of this study is to investigate the application of machine learning algorithms and statistical time series forecasting methods in modelling the financial time series data. The models implemented including Decision Tree Regression, Random Forest Regression, Polynomial Regression, K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), Autoregressive Integrated Moving Average (ARIMA), and Exponential Smoothing (ETS). The benchmark that used for comparison in this study is the previous study that done by Mambu et al. (2020). The best model has been proposed as forecasting model after comparison in this study. In addition, dashboards have been developed by using Tableau Desktop for visualization in this study. The best model obtained for the EXCL and ISAT dataset is the Polynomial Regression model with RMSE 0.0008 and 0.0036 respectively. The best model obtained for the FREN dataset is the Artificial Neural Network (ANN) model with RMSE 0.0863. The best model obtained for the TLKM dataset is the Random Forest model with RMSE 0.0029. shafika UTM 125 p. Thesis (Master of Science (Data Science)) - Universiti Teknologi Malaysia, 2023 2025-03-06T09:57:43Z 2025-03-06T09:57:43Z 2023 Master's thesis https://utmik.utm.my/handle/123456789/40419 vital:152845 valet-20230820-083959 ENG Closed Access UTM Complete Unpublished Completion application/pdf Universiti Teknologi Malaysia
spellingShingle Computing
Fong, Lee Ling
Forecasting of telecommunication stock prices using machine learning algorithms
thesis_level Master
title Forecasting of telecommunication stock prices using machine learning algorithms
title_full Forecasting of telecommunication stock prices using machine learning algorithms
title_fullStr Forecasting of telecommunication stock prices using machine learning algorithms
title_full_unstemmed Forecasting of telecommunication stock prices using machine learning algorithms
title_short Forecasting of telecommunication stock prices using machine learning algorithms
title_sort forecasting of telecommunication stock prices using machine learning algorithms
topic Computing
url https://utmik.utm.my/handle/123456789/40419
work_keys_str_mv AT fongleeling forecastingoftelecommunicationstockpricesusingmachinelearningalgorithms