2025· Proceedings of the 3rd International Conference on Data Science, Advanced Algorithms, and Intelligent Computing· 0 citations· 18 references
TL;DR
This paper systematically reviews three categories of key indicators influencing stock price fluctuations: technical, fundamental, and investor sentiment indicators, and demonstrates that combination models significantly enhance forecasting accuracy and stability by leveraging complementary strengths across models.
Abstract
: In the context of growing complexity in financial market data, traditional single forecasting models face significant challenges in achieving high-precision stock price predictions. Combination forecasting models have emerged as a robust solution by integrating multi-source information and diverse methodologies. This paper systematically reviews three categories of key indicators influencing stock price fluctuations: technical, fundamental, and investor sentiment indicators. It critically examines the benefits and drawbacks associated with different models, as standard statistical models, machine learning methods, and neural network topologies. Based on their integration mechanisms, combination models are classified into linear, nonlinear, and hybrid types, with in-depth discussions on their theoretical frameworks and empirical applications. Through comparative analysis, it is demonstrated that combination models significantly enhance forecasting accuracy and stability by leveraging complementary strengths across models. The paper concludes with an exploration of current challenges and future research directions, emphasizing the need for improved interpretability and dynamic adaptability in real-world financial environments.
This paper finds that the hybrid model yields higher prediction accuracy and smaller errors than the single model by comparing the results of both models.
Hui-Hui Chen, Ze-Yuan Li· Proceedings of the 3rd Inter...· 0 citations
This work introduces a robust framework to predict daily log returns by leveraging a combined dataset comprising historical data, TIs, and macroeconomic data, including gold and oil prices, and macroeconomic data, including gold and oil prices, the volatility index, the dollar index, the interest rate, the 10-year Trea...
Aya Nabil, S. Barakat, Ahmed Aboelfetouh et al.· Scientific Reports· 0 citations
The results highlight the significance of using alternative information on sentiment along with traditional market indicators and show that the machine learning techniques outperform other techniques especially LSTM.
S. Durga, B. Ratnavalli, Visalakshi Naraparedd et al.· International Academic Journ...· 0 citations
A primary insight is that future research should move towards integrating these complementary methodologies and leveraging multi-modal data sources, which holds the potential for developing more robust and economically interpretable predictive frameworks.
Yan-Lin Huang· Advances in Economics, Manag...· 0 citations
The empirical results demonstrate that machine learning models significantly outperform OLS in capturing complex nonlinear relationships in stock returns, and the ANN model achieves the lowest RMSE, indicating the highest predictive accuracy, and generates superior long–short portfolio returns compared to the other mod...
Phat Ly Huynh Ngo, T. Pham, B. Lệ· Tạp chí Khoa học Đại học Côn...· 0 citations
The findings indicate that forecasting performance is strongly context-dependent: classical models remain effective for relatively stationary univariate series, volatility-oriented models are particularly relevant when clustering and spillover effects are present, and deep learning and transformer-based approaches are...
Elia Setiana, Kusrini Kusrini, Tonny Hidayat et al.· JITK (Jurnal Ilmu Pengetahua...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.