A Gaussian additive model based on the stacking framework and its application in stock price forecasting

Kai Chen; Mengyao Sun; Shuaichen Ge

doi:10.62051/c4vm8x80

Authors

Kai Chen
Mengyao Sun
Shuaichen Ge

DOI:

https://doi.org/10.62051/c4vm8x80

Keywords:

Stock Price Prediction; Stacking Algorithm; Gaussian Process Additive Model; Uncertainty Quantification.

Abstract

With the rapid development of big data technologies, employing stock price prediction models has become crucial in quantitative finance. Among the various prediction models, selecting appropriate features, mining factors, and quantifying the uncertainty of stock prices are essential challenges. To address these issues, in this paper proposes an improved Gaussian Process Additive Model based on the stacking method. The proposed approach introduces a "re-encoding and reduction" design in the first layer of the stacking framework, effectively filtering redundant features. Furthermore, the method uses the Gaussian Process Additive Model in the second layer of the stacking framework to capture interactions between features. By incorporating a Gaussian process prior, the model can provide uncertainty estimates for the predictions. Additionally, the flexibility in selecting sub-models and kernel functions within the Gaussian additive framework enhances the method's capacity to fit complex functions, offering a high degree of flexibility. Both simulation experiments and real-world data analysis demonstrate that the proposed method is highly competitive compared to other classical prediction models.

Downloads

Download data is not yet available.

References

[1] Anand C. Comparison of stock price prediction models using pre-trained neural networks [J]. Journal of Ubiquitous Computing and Communication Technologies, 2021, 3 (2): 122 - 134.

[2] Gao Z, Tsay R S. A structural‐factor approach to modeling high‐dimensional time series and space‐time data [J]. Journal of Time Series Analysis, 2019, 40 (3): 343 - 362.

[3] Ando T, Bai J. Clustering huge number of financial time series: A panel data approach with high-dimensional predictors and factor structures [J]. Journal of the American Statistical Association, 2017, 112 (519): 1182 - 1198.

[4] Ekblom J. Decision Making under Uncertainty in Financial Markets: improving decisions with stochastic optimization[M]. Linköping University Electronic Press, 2018.

[5] Khanderwal S, Mohanty D. Stock price prediction using ARIMA model [J]. International Journal of Marketing & Human Resource Research, 2021, 2 (2): 98 - 107.

[6] Mahadik A, Vaghela D, Mhaisgawali A. Stock price prediction using lstm and arima [C]//2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE, 2021: 1594 - 1601.

[7] Naik N, Mohan B R, Jha R A. GARCH model identification for stock crises events [J]. Procedia Computer Science, 2020, 171: 1742 - 1749.

[8] Gao Z, He Y, Kuruoglu E E. A hybrid model integrating LSTM and GARCH for Bitcoin price prediction [C]//2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2021: 1 - 6.

[9] Ma Q. Comparison of ARIMA, ANN and LSTM for stock price prediction [C]//E3S Web of Conferences. EDP Sciences, 2020, 218: 01026.

[10] Ho M K, Darman H, Musa S. Stock price prediction using ARIMA, neural network and LSTM models [C]//Journal of Physics: Conference Series. IOP Publishing, 2021, 1988 (1): 012041.

[11] Inglada-Perez L. A comprehensive framework for uncovering non-linearity and Chaos in financial markets: Empirical evidence for four major stock market indices[J]. Entropy, 2020, 22 (12): 1435.

[12] Hossain M R, Ismail M T, Karim S A B A. Improving stock price prediction using combining forecasts methods [J]. IEEE Access, 2021, 9: 132319 - 132328.

[13] Hushani P. Using autoregressive modelling and machine learning for stock market prediction and trading [C]//Third International Congress on Information and Communication Technology: ICICT 2018, London. Springer Singapore, 2019: 767 - 774.

[14] Wei Z, Dai B, Lin D. Factor investing with a deep multi-factor model [J]. arXiv preprint arXiv: 2210.12462, 2022.

[15] Cheng P, Mao F, Zhao H. Relationship Study of Meltblowning Variables Based on Machine Learning Algorithm [J]. Automation and Machine Learning, 2022, 3 (2): 17 - 26.

[16] Wu, Y. Stock Price Prediction Based on Simple Decision Tree, Random Forest, and XGBoost [J]. BCP Business & Management, 2023.

[17] Jiang M, Liu J, Zhang L, et al. An improved Stacking framework for stock index prediction by leveraging tree-based ensemble models and deep learning algorithms [J]. Physica A: Statistical Mechanics and its Applications, 2020, 541: 122272.

[18] Xiaosong Z, Qiangfu Z. Stock prediction using optimized LightGBM based on cost awareness [C]//2021 5th IEEE International Conference on Cybernetics (CYBCONF). IEEE, 2021: 107 - 113.

[19] Costa A B R, Ferreira P C G, Gaglianone W P, et al. Machine learning and oil price point and density forecasting [J]. Energy Economics, 2021, 102: 105494.

[20] Ampomah E K, Qin Z, Nyame G. Evaluation of tree-based ensemble machine learning models in predicting stock price direction of movement [J]. Information, 2020, 11 (6): 332.

[21] Chong L S, Lim K M, Lee C P. Stock market prediction using ensemble of Deep Neural Networks [C]//2020 IEEE 2nd international conference on artificial intelligence in engineering and technology (IICAIET). IEEE, 2020: 1 - 5.

[22] Yang C, Zhai J, Tao G. Deep learning for price movement prediction using convolutional neural network and long short‐term memory [J]. Mathematical Problems in Engineering, 2020, 2020 (1): 2746845.

[23] Barrash S, Shen Y, Giannakis G B. Scalable and adaptive KNN for regression over graphs [C]//2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP). IEEE, 2019: 241 - 245.

[24] Ranstam J, Cook J A. LASSO regression [J]. Journal of British Surgery, 2018, 105 (10): 1348 - 1348.

[25] Yuchi W, Gombojav E, Boldbaatar B, et al. Evaluation of random forest regression and multiple linear regression for predicting indoor fine particulate matter concentrations in a highly polluted city [J]. Environmental pollution, 2019, 245: 746 - 753.