Predicting Economic Advantages in Smart Innovative City Development: A CSO-MCNN Approach

Yao Guo () and Huwei Li
Additional contact information
Yao Guo: Zhengzhou Vocational College of Finance and Taxation
Huwei Li: Henan Institute of Economics and Trade

Journal of the Knowledge Economy, 2024, vol. 15, issue 4, No 175, 20299-20319

Abstract: Abstract The rapid emergence of smart cities has captured global attention for their potential economic impact. These cities leverage information technology, artificial intelligence, and data analysis to enhance productivity, resource efficiency, and innovation. This paper explores the economic advantages associated with smart innovative city development and presents a novel CSO-MCNN model for economic forecasting. The key contributions of this research include an improved convolutional neural network (CNN) architecture for time series feature extraction, the integration of Dilated Convolutions with Causal Convolutions, and the optimization of convolutional and pooling layer weights using the CS algorithm. The CSO-MCNN model exhibits remarkable performance in economic forecasting, offering potential benefits in investment decision-making and resource allocation. Its unique design reduces parameter complexity while preserving the chronological order of features critical for predicting economic trends. Leveraging financial data from 36 companies spanning 2008 to 2022, the model demonstrates commendable predictive accuracy, making it a valuable tool for investors and decision-makers. The CSO-MCNN shows extraordinary performance advantages, with MAE and RMSE reduced by approximately 46.36% and 47.98%, respectively, compared to its predecessor. However, deep learning models like CSO-MCNN have inherent limitations, including their “black box” nature and complexity. While they excel in economic prediction tasks, their theoretical foundations remain a challenge. Nevertheless, the model’s enhanced predictive prowess holds promise for practical applications, offering data-driven strategies to maximize returns and minimize risks in smart city development. This study sets the stage for future research exploring the model’s applicability across diverse prediction targets, data characteristics, and interdisciplinary approaches. By integrating CSO-MCNN with multimodal data and collaborative efforts, we can further advance economic and financial forecasting in the context of smart cities, enriching our understanding of these innovative urban environments.

Keywords: Smart cities; Deep learning; CSO-MCNN model; Time series analysis; Financial data (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13132-024-01939-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jknowl:v:15:y:2024:i:4:d:10.1007_s13132-024-01939-4

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/13132

DOI: 10.1007/s13132-024-01939-4

Access Statistics for this article

Journal of the Knowledge Economy is currently edited by Elias G. Carayannis

More articles in Journal of the Knowledge Economy from Springer, Portland International Center for Management of Engineering and Technology (PICMET)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().