A Two-stage Model: Investment Market Trading Model Based on Prediction and Adaptive Strategies
Keywords:Two-stage model; ARIMA-LSTM; CEEMDAN; Quantitative trading indicators; Semi-supervised SVM; Adaptive strategy.
Market traders buy and sell volatile assets frequently, with a goal to maximize their total return. Two such assets are gold and bitcoin. This paper constructs a two-stage model for price prediction and trading strategy formulation. Firstly, we build a dynamic ARIMA-LSTM hybrid model. And before applying it, we use CEEMDAN method to decompose the non-stationary time series first and then reconstruct the final result by predicting each IMF and summing up weighted. And then the model can update the training set dynamically when new price data is released. After getting prices predicted, we calculated several quantitative trading indicators so that we can make decisions more comprehensively instead of only focusing on the predicted price. And we use semi-supervised SVM to develop an adaptive strategy to maximize the total return. Finally, we demonstrate the superiority of our strategy from two perspectives. In actual investment transactions, the two-stage model can be used as a guide for the formulation of trading strategies, thereby avoiding risks and increasing returns.
He Y, Li J M, Ruan S M and Zhao S P. A Hybrid Model for Financial Time Series Forecasting—Integration of EWT, ARIMA With the Improved ABC Optimized ELM [J]. IEEE Access, 2020, (8). DOI: https://doi.org/10.1109/ACCESS.2020.2987547
Rahimi Z H and Khashei M. A Least Squares-based Parallel Hybridization of Statistical and Intelligent Models for Time Series Forecasting [J]. Computers & Industrial Engineering, 2018, (11). DOI: https://doi.org/10.1016/j.cie.2018.02.023
Bao W, Yue J, Rao Y and Boris P. A deep learning framework for financial time series using stacked autoencoders and long-short term memory [J]. PLOS ONE, 2017, 12(7): e0180944. DOI: https://doi.org/10.1371/journal.pone.0180944
Ravi C. Fuzzy Crow Search Algorithm-Based Deep LSTM for Bitcoin Prediction [J]. International Journal of Distributed Systems and Technologies (IJDST), 2020, 11(4): 53-71. DOI: https://doi.org/10.4018/IJDST.2020100104
Sun Y, Zhao Z J, Ma X B and Du Z H. Short-time Scale Gravitational Microlensing Events Prediction With ARIMA-LSTM and ARIMA-GRU Hybrid Model [J]. Lecture Notes in Computer cience, 2019, (11473). DOI: https://doi.org/10.1007/978-3-030-28061-1_23
Torres M E, Colominas M, Schlotthuer G and Flandrin P. A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise [J]. Brain Research Bulletin, 2011, 125(3): 4144-4147. DOI: https://doi.org/10.1109/ICASSP.2011.5947265
He Y Y, Li P and Han J B. Research on Predictive Modeling on Stock Market Index Based on CEEMDAN-LSTM [J]. Journal of Statistics and Information, 2020, 35(06): 34-45.
Kim K J. Financial time series forecasting using support vector machines [J]. Neurocomputing, 2003, 55 (1): 307-319. DOI: https://doi.org/10.1016/S0925-2312(03)00372-2
Sakthivel N R, Sugumaran V and Nair B B. Comparison of decision tree-fuzzy and rough set fuzzy methods for fault categorization of mono-block centrifugal pump [J]. Mechanical Systems & Signal Processing, 2010, 24 (6): 1887-1906. DOI: https://doi.org/10.1016/j.ymssp.2010.01.008
Harris T. Credit scoring using the clustered support vector machine [J]. Expert Systems with Applications, 2015, 42(2): 741 -750. DOI: https://doi.org/10.1016/j.eswa.2014.08.029
Li W X, Li J Q, Economics S O and University J. Improvement of Semi-supervised Kernel Clustering Algorithm Based on Multi-factor Stock Selection [J]. Journal of Statistics and Information, 2018, 33(03): 30-36.
Lv K C, Yan H F and Chen C. Quantitative Investment Strategy Based on CSI 300 [J]. Journal of Guangxi Normal University (Natural Science Edition), 2019, 37(01): 1-12.
How to Cite
This work is licensed under a Creative Commons Attribution 4.0 International License.