Improvements of Time Series Prediction Models for ExxonMobil Based on Moving Averages

Wenjie Deng

2024

Abstract

Time series forecasting plays a crucial role in financial analysis, especially in predicting stock prices and guiding investment strategies. In this study, ExxonMobil will be used as the research object to test a price prediction model based on moving averages. The data is derived from historical stock data provided by Yahoo Finance, and metrics such as the 10-day Simple Moving Average (SMA), 20-Day Exponential Moving Average (EMA), Relative Strength Index (RSI), and Moving Average Convergence Divergence (MACD) from Python's stockstat library are added to the model as enhancements to the historical forecasting model. The enhanced model fits well, with an R-square value of 0.8546, showing significant prediction accuracy. While the model is effective in capturing the overall trend, it is less consistent with the actual performance of the market during periods of high volatility. For petrochemical module companies, the impact of international oil prices and geopolitical events cannot be ignored. These results suggest that adding industry-specific dynamic-specific technical indicators to forecasting models can greatly improve stock price forecasts, thereby providing valuable insights for financial analysts and investors who focus on the energy market.

Paper Citation

in Harvard Style

Deng W. (2024). Improvements of Time Series Prediction Models for ExxonMobil Based on Moving Averages. In Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI; ISBN 978-989-758-726-9, SciTePress, pages 510-515. DOI: 10.5220/0013269700004568

in Bibtex Style

@conference{ecai24,
author={Wenjie Deng},
title={Improvements of Time Series Prediction Models for ExxonMobil Based on Moving Averages},
booktitle={Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI},
year={2024},
pages={510-515},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013269700004568},
isbn={978-989-758-726-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence - Volume 1: ECAI
TI - Improvements of Time Series Prediction Models for ExxonMobil Based on Moving Averages
SN - 978-989-758-726-9
AU - Deng W.
PY - 2024
SP - 510
EP - 515
DO - 10.5220/0013269700004568
PB - SciTePress