Open Access

ARTICLE

Exploiting Data Science for Measuring the Performance of Technology Stocks

by Tahir Sher¹, Abdul Rehman², Dongsun Kim^2,*, Imran Ihsan¹

1 Department of Creative Technologies, Air University, Islamabad, 44230, Pakistan
2 School of Computer Science and Engineering, Kyungpook National University, Daegu, 41566, Korea

* Corresponding Author: Dongsun Kim. Email:

(This article belongs to the Special Issue: Data Science for the Internet of Things)

Computers, Materials & Continua 2023, 76(3), 2979-2995. https://doi.org/10.32604/cmc.2023.036553

Received 04 October 2022; Accepted 22 February 2023; Issue published 08 October 2023

Abstract

The rise or fall of the stock markets directly affects investors’ interest and loyalty. Therefore, it is necessary to measure the performance of stocks in the market in advance to prevent our assets from suffering significant losses. In our proposed study, six supervised machine learning (ML) strategies and deep learning (DL) models with long short-term memory (LSTM) of data science was deployed for thorough analysis and measurement of the performance of the technology stocks. Under discussion are Apple Inc. (AAPL), Microsoft Corporation (MSFT), Broadcom Inc., Taiwan Semiconductor Manufacturing Company Limited (TSM), NVIDIA Corporation (NVDA), and Avigilon Corporation (AVGO). The datasets were taken from the Yahoo Finance API from 06-05-2005 to 06-05-2022 (seventeen years) with 4280 samples. As already noted, multiple studies have been performed to resolve this problem using linear regression, support vector machines, deep long short-term memory (LSTM), and many other models. In this research, the Hidden Markov Model (HMM) outperformed other employed machine learning ensembles, tree-based models, the ARIMA (Auto Regressive Integrated Moving Average) model, and long short-term memory with a robust mean accuracy score of 99.98. Other statistical analyses and measurements for machine learning ensemble algorithms, the Long Short-Term Model, and ARIMA were also carried out for further investigation of the performance of advanced models for forecasting time series data. Thus, the proposed research found the best model to be HMM, and LSTM was the second-best model that performed well in all aspects. A developed model will be highly recommended and helpful for early measurement of technology stock performance for investment or withdrawal based on the future stock rise or fall for creating smart environments.

---

Keywords

---