Integrating singular spectrum analysis and nonlinear autoregressive neural network for stock price forecasting

Fathi, Asmaa Y.; El-Khodary, Ihab A.; Saafan, Muhammad

doi:10.11591/ijai.v11.i3.pp851-858

Cited by 2 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hassani et al also found that SSA outperforms several singles models such as ARIMA, ETS, NN, Trigonometric Box-Cox ARMA Trend Seasonal (TBATS), and Fractionalized ARIMA (ARFIMA) to predict tourism demand in European countries. Fathi et al (2022) combined SSA and nonlinear autoregressive neural networks (NARNN) to predict 24 stock prices and compared them with ARIMA and NARNN. Their results also showed that SSA combined with NARNN provides better forecasting performance than ARIMA and NARNN.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models

Palazzi

Maçaira

Meira

et al. 2023

Prod.

View full text Add to dashboard Cite

Paper aims: To predict monthly corn, soybean, and sugar spot prices in Brazil using hybrid forecasting techniques.Originality: This study combines the Singular Spectrum Analysis with different forecasting methods.Research method: This paper presents a set of hybrid forecasting approaches combining Singular Spectrum Analysis (SSA) with different univariate time series methods, ranging from complex seasonality methods to machine learning and autoregressive models to predict monthly corn, soybean, and sugar spot prices in Brazil. We carry out a range of out-ofsample forecasting experiments and use a comprehensive set of forecast evaluation metrics. We contrast the performance of the proposed approaches with that of a range of benchmark models. Main findings:The results show that the proposed hybrid models present better performances, with the hybrid SSA-neural network approach providing the most competitive results in our sample.Implications for theory and practice: Forecasting agricultural prices is of paramount importance to assist producers, farmers, and the industry in decision-making processes.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models

Palazzi

Maçaira

Meira

et al. 2023

Prod.

View full text Add to dashboard Cite

show abstract

“…Their research employs machine learning methodologies to analyze the impact of economic uncertainty on stock market dynamics, highlighting the role of sentiment analysis in understanding stock market behavior. Asmaa Y. Fathi, Ihab A. El-Khodary, and Muhammad Saafan [4] explored the integration of singular spectrum analysis and nonlinear autoregressive neural networks for stock price forecasting. Their study represents an innovative approach to stock price prediction, emphasizing the importance of advanced computational techniques in financial modeling.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Stock Portfolio with Global Economic Factors using Dynamic Data Modelling

B Varija

2023

IJRITCC

View full text Add to dashboard Cite

This article analyzes stock portfolios and worldwide economic challenges. This study uses APIs to retrieve data and analyze correlations. To determine and measure how economic indicators affect stock performance. This work introduces an autoencoder-based model to better comprehend the complex relationship between economic conditions and stock portfolio dynamics. The analysis begins with an API retrieval of a wide range of macroeconomic information. These indicators include global economic metrics like GDP, unemployment, CPI, federal funds rates, and treasury bill rates. After collection, data is carefully curated and prepared for analysis. This study uses correlation analysis to understand economic variables and stock portfolio performance. This study explores how economic conditions affect stock prices and portfolio returns. This study seeks to discover trends, dependencies, and future issues that may affect investment decisions. This study also introduces an autoencoder-based neural network model to capture complex nonlinear relationships between economic variables and stock portfolio behavior. Deep learning improves interpretability and prediction, allowing a better understanding of the complex financial ecosystem dynamics. The inquiry provides valuable insights for investors, financial experts, and regulators. This study advances data-driven investment and risk management solutions. The autoencoder-based approach also reveals latent structures and hidden factors that affect stock portfolios. This novel approach opens new study options. In conclusion, this study provides a thorough stock portfolio analysis approach for global economic challenges. API data retrieval, correlation analysis, and a novel autoencoder model are used in this work to better understand the complicated relationships between economic indicators and financial markets. These insights can improve investment and policy decisions in a more integrated and dynamic global economy.

show abstract

Integrating singular spectrum analysis and nonlinear autoregressive neural network for stock price forecasting

Cited by 2 publications

References 25 publications

Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models

Forecasting commodity prices in Brazil through hybrid SSA-complex seasonality models

Analysis of Stock Portfolio with Global Economic Factors using Dynamic Data Modelling

Contact Info

Product

Resources

About