Multi-Objective System Predicting Based on Hybrid LSTM-Markov and GSRF Models
DOI:
https://doi.org/10.62051/vm5zjw29Keywords:
Multi-objective system; LSTM, Markov chain; Zero-inflation; Grid Search Random Forest.Abstract
The prediction of multi-objective complex systems has always been one of the significant challenges in academia. The multi-dimensional structure, diverse distribution, and complex temporal dependencies of the data make it difficult for conventional mathematical models to perform effective analysis. This study explores the application of hybrid machine learning algorithms in predicting multi-objective systems. This paper developed an LSTM-Markov model which uses the Markov chain to optimize the preliminary predictive results obtained by LSTM. A Grid Search-optimized Random Forest (GSRF) model was integrated with the LSTM-Markov model to address the zero-inflated and long-tailed characteristics of the chosen datasets. The GSRF model was a powerful non-linear classifier that could resolve the zero-inflated outputs. Using Olympic medal counts prediction as the case, the final evaluation metrics of LSTM-Markov revealed that the MSE and R-squared value of the LSTM-Markov model were 0.12 and 0.89 respectively, indicating significant improvements upon baseline methods. The classification accuracy of GSRF achieved 95.52%, demonstrating promising performance in classification and forecasting. This study provides an innovative approach to solving the multi-target predicting problems of complex time series systems. The method also holds significant application potential in areas such as financial risk prediction and disease transmission modeling.
Downloads
References
[1] Zheng Y, Wang D X. A survey of recommender systems with multi-objective optimization[J]. Neurocomputing, 2022, 474: 141-153. DOI: https://doi.org/10.1016/j.neucom.2021.11.041
[2] Nagpal P, Gupta K, Verma Y, et al. Paris Olympic Medal Tally Prediction[C]//International Conference on Data Management, Analytics & Innovation. Singapore: Springer Nature Singapore, 2023: 249-267.
[3] Schlembach C, Schmidt S L, Schreyer D, et al. Forecasting the Olympic medal distribution–a socioeconomic machine learning model[J]. Technological Forecasting and Social Change, 2022, 175: 121314. DOI: https://doi.org/10.1016/j.techfore.2021.121314
[4] Zhao S, Cao J, Steve J. Research on Olympic medal prediction based on GA-BP and logistic regression model[J]. F1000Research, 2025, 14: 245. DOI: https://doi.org/10.12688/f1000research.161865.2
[5] Wang F, Li Y, Liao F, et al. An ensemble learning based prediction strategy for dynamic multi-objective optimization[J]. Applied Soft Computing, 2020, 96: 106592. DOI: https://doi.org/10.1016/j.asoc.2020.106592
[6] Wang Y, Wang J, Yang J, et al. STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization[J]. arXiv preprint arXiv:2501.17711, 2025.
[7] Nagpal P, Gupta K, Verma Y, et al. Paris Olympic (2024) Medal Tally Prediction[C]//International Conference on Data Management, Analytics & Innovation. Singapore: Springer Nature Singapore, 2023: 249-267. DOI: https://doi.org/10.1007/978-981-99-1414-2_20
[8] Yu Y, Si X, Hu C, et al. A review of recurrent neural networks: LSTM cells and network architectures[J]. Neural computation, 2019, 31(7): 1235-1270. DOI: https://doi.org/10.1162/neco_a_01199
[9] DiPietro R, Hager G D. Deep learning: RNNs and LSTM[M]//Handbook of medical image computing and computer assisted intervention. Academic Press, 2020: 503-519. DOI: https://doi.org/10.1016/B978-0-12-816176-0.00026-0
[10] Landi F, Baraldi L, Cornia M, et al. Working memory connections for LSTM[J]. Neural Networks, 2021, 144: 334-341. DOI: https://doi.org/10.1016/j.neunet.2021.08.030
[11] Hassani H, Yeganegi M R. Sum of squared ACF and the Ljung–Box statistics[J]. Physica A: Statistical Mechanics and its Applications, 2019, 520: 81-86. DOI: https://doi.org/10.1016/j.physa.2018.12.028
[12] Stewart W J. Introduction to the numerical solution of Markov chains[J]. 2021. DOI: https://doi.org/10.2307/j.ctv182jsw5
[13] Wang Y, Wang J, Huang T Y, et al. STGCN-LSTM for Olympic Medal Prediction: Dynamic Power Modeling and Causal Policy Optimization[J]. arXiv preprint arXiv:2501.17711, 2025.
[14] Ma X, Wang Z. Performance and Score Analysis of Athletes Based on EWM-TOPSIS Algorithm and GSRF Prediction Model[C]//2024 IEEE 2nd International Conference on Sensors, Electronics and Computer Engineering (ICSECE). IEEE, 2024: 933-937. DOI: https://doi.org/10.1109/ICSECE61636.2024.10729480
[15] Genuer R, Poggi J M, Genuer R, et al. Random forests[M]. Springer International Publishing, 2020. DOI: https://doi.org/10.1007/978-3-030-56485-8
[16] Ahmad G N, Fatima H, Ullah S, et al. Efficient medical diagnosis of human heart diseases using machine learning techniques with and without GridSearchCV[J]. Ieee Access, 2022, 10: 80151-80173. DOI: https://doi.org/10.1109/ACCESS.2022.3165792
[17] Prakash S, Jalal A S, Pathak P. Forecasting covid-19 pandemic using prophet, lstm, hybrid gru-lstm, cnn-lstm, bi-lstm and stacked-lstm for india[C]//2023 6th International Conference on information systems and computer networks (ISCON). IEEE, 2023: 1-6. DOI: https://doi.org/10.1109/ISCON57294.2023.10112065
[18] Kumar D, Kothiyal A, Kumar R, et al. Random Forest approach optimized by the Grid Search process for predicting the dropout students[C]//2024 International Conference on Innovations and Challenges in Emerging Technologies (ICICET). IEEE, 2024: 1-6. DOI: https://doi.org/10.1109/ICICET59348.2024.10616372
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
