Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting
Financial Time Series Forecasting (TSF) remains a critical challenge in Artificial Intelligence (AI) due to the inherent complexity of financial data, characterized by strong non-linearity, dynamic non-stationarity, and multi-factor coupling. To address the performance limitations of Spiking Neural...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/5/262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255288562614272 |
|---|---|
| author | Panke Qin Yongjie Ding Ya Li Bo Ye Zhenlun Gao Yaxing Liu Zhongqi Cai Haoran Qi |
| author_facet | Panke Qin Yongjie Ding Ya Li Bo Ye Zhenlun Gao Yaxing Liu Zhongqi Cai Haoran Qi |
| author_sort | Panke Qin |
| collection | DOAJ |
| description | Financial Time Series Forecasting (TSF) remains a critical challenge in Artificial Intelligence (AI) due to the inherent complexity of financial data, characterized by strong non-linearity, dynamic non-stationarity, and multi-factor coupling. To address the performance limitations of Spiking Neural Networks (SNNs) caused by hyperparameter sensitivity, this study proposes an SNN model optimized by an Improved Cuckoo Search (ICS) algorithm (termed ICS-SNN). The ICS algorithm enhances global search capability through piecewise-mapping-based population initialization and introduces a dynamic discovery probability mechanism that adaptively increases with iteration rounds, thereby balancing exploration and exploitation. Applied to futures market price difference prediction, experimental results demonstrate that ICS-SNN achieves reductions of 13.82% in MAE, 21.27% in MSE, and 15.21% in MAPE, while improving the coefficient of determination (R<sup>2</sup>) from 0.9790 to 0.9822, compared to the baseline SNN. Furthermore, ICS-SNN significantly outperforms mainstream models such as Long Short-Term Memory (LSTM) and Backpropagation (BP) networks, reducing prediction errors by 10.8% (MAE) and 34.9% (MSE), respectively, without compromising computational efficiency. This work highlights that ICS-SNN provides a biologically plausible and computationally efficient framework for complex financial TSF, bridging the gap between neuromorphic principles and real-world financial analytics. The proposed method not only reduces manual intervention in hyperparameter tuning but also offers a scalable solution for high-frequency trading and multi-modal data fusion in future research. |
| format | Article |
| id | doaj-art-5cf5a1d02a63498baa1e6dff3bfe1bfd |
| institution | OA Journals |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-5cf5a1d02a63498baa1e6dff3bfe1bfd2025-08-20T01:56:55ZengMDPI AGAlgorithms1999-48932025-05-0118526210.3390/a18050262Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series ForecastingPanke Qin0Yongjie Ding1Ya Li2Bo Ye3Zhenlun Gao4Yaxing Liu5Zhongqi Cai6Haoran Qi7School of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaNingbo Artificial Intelligence Institute, Shanghai Jiaotong University, Ningbo 315000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo 454000, ChinaFinancial Time Series Forecasting (TSF) remains a critical challenge in Artificial Intelligence (AI) due to the inherent complexity of financial data, characterized by strong non-linearity, dynamic non-stationarity, and multi-factor coupling. To address the performance limitations of Spiking Neural Networks (SNNs) caused by hyperparameter sensitivity, this study proposes an SNN model optimized by an Improved Cuckoo Search (ICS) algorithm (termed ICS-SNN). The ICS algorithm enhances global search capability through piecewise-mapping-based population initialization and introduces a dynamic discovery probability mechanism that adaptively increases with iteration rounds, thereby balancing exploration and exploitation. Applied to futures market price difference prediction, experimental results demonstrate that ICS-SNN achieves reductions of 13.82% in MAE, 21.27% in MSE, and 15.21% in MAPE, while improving the coefficient of determination (R<sup>2</sup>) from 0.9790 to 0.9822, compared to the baseline SNN. Furthermore, ICS-SNN significantly outperforms mainstream models such as Long Short-Term Memory (LSTM) and Backpropagation (BP) networks, reducing prediction errors by 10.8% (MAE) and 34.9% (MSE), respectively, without compromising computational efficiency. This work highlights that ICS-SNN provides a biologically plausible and computationally efficient framework for complex financial TSF, bridging the gap between neuromorphic principles and real-world financial analytics. The proposed method not only reduces manual intervention in hyperparameter tuning but also offers a scalable solution for high-frequency trading and multi-modal data fusion in future research.https://www.mdpi.com/1999-4893/18/5/262cuckoo search algorithmspiking neural networksfinancial time series forecastinghyperparameter setting |
| spellingShingle | Panke Qin Yongjie Ding Ya Li Bo Ye Zhenlun Gao Yaxing Liu Zhongqi Cai Haoran Qi Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting Algorithms cuckoo search algorithm spiking neural networks financial time series forecasting hyperparameter setting |
| title | Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting |
| title_full | Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting |
| title_fullStr | Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting |
| title_full_unstemmed | Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting |
| title_short | Spiking Neural Networks Optimized by Improved Cuckoo Search Algorithm: A Model for Financial Time Series Forecasting |
| title_sort | spiking neural networks optimized by improved cuckoo search algorithm a model for financial time series forecasting |
| topic | cuckoo search algorithm spiking neural networks financial time series forecasting hyperparameter setting |
| url | https://www.mdpi.com/1999-4893/18/5/262 |
| work_keys_str_mv | AT pankeqin spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT yongjieding spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT yali spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT boye spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT zhenlungao spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT yaxingliu spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT zhongqicai spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting AT haoranqi spikingneuralnetworksoptimizedbyimprovedcuckoosearchalgorithmamodelforfinancialtimeseriesforecasting |