A novel real-time multi-step forecasting system with a three-stage data preprocessing strategy for containerized freight market

Yin, Kedong; Guo, Hongbo; Yang, Wendong

doi:10.1016/j.eswa.2024.123141

Cited by 1 publication

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This phase involves a series of tasks aimed at cleaning, transforming, and preparing the data to facilitate meaningful analysis and model training. By addressing issues such as missing values, outliers, and data inconsistencies, data preprocessing lays the foundation for accurate and reliable predictive modeling [25], [26].…”

Section: Data Preprocessingmentioning

confidence: 99%

Harnessing the Power of Prophet Algorithm for Advanced Predictive Modeling of Grab Holdings Stock Prices

Hery

2024

J. Appl. Data Sci.

View full text Add to dashboard Cite

This study investigates the effectiveness of the Prophet algorithm in predicting Grab Holdings' stock prices dataset from Kaggle. By meticulously analyzing historical closing, high, low, and volume data, the research aims to uncover market patterns and gain insights into investor sentiment based on short-term forecasting. The findings reveal a dynamic trajectory for Grab Holdings' stock, characterized by significant fluctuations and evolving investor confidence. The stock reached a peak of $14 in early 2022, indicating optimism, but subsequently experienced a decline to $4 by late 2023, reflecting a shift in sentiment. Notably, 2023 witnessed heightened volatility compared to 2022, evident in more significant price swings and increased trading volume. The Prophet algorithm demonstrated promising potential for prediction better than traditional methods, which overlook the presence of seasonality or fail to adapt to evolving market conditions, leading to less accurate forecasts. The excellent performance of Prophet is indicated by a Mean Absolute Percentage Error (MAPE) of 10.45511%, a Mean Absolute Error (MAE) of 3.112026, and a Root Mean Squared Error (RMSE) of 3.516969. Compared to the traditional ARIMA, MAE and RMSE resulting from Prophet are much lower than their counterparts, which are 14.49675 and 16.079898, respectively. These widely used metrics suggest moderate accuracy in predicting future stock prices. This research offers valuable insights for investors that they can use to understand the trend of Grab Holdings' stock price and make more informed investment decisions regarding buying or selling opportunities. However, it is crucial to acknowledge the inherent limitations of such models and interpret results cautiously, considering the ever-changing dynamics of the financial market.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Harnessing the Power of Prophet Algorithm for Advanced Predictive Modeling of Grab Holdings Stock Prices

Hery

2024

J. Appl. Data Sci.

View full text Add to dashboard Cite

show abstract

A novel real-time multi-step forecasting system with a three-stage data preprocessing strategy for containerized freight market

Cited by 1 publication

References 55 publications

Harnessing the Power of Prophet Algorithm for Advanced Predictive Modeling of Grab Holdings Stock Prices

Harnessing the Power of Prophet Algorithm for Advanced Predictive Modeling of Grab Holdings Stock Prices

Contact Info

Product

Resources

About