A Team-Innovative Optimization Search Algorithm and its Application to Cash Flow Forecasting

JianJun Wu and Lu Xia ()
Additional contact information
JianJun Wu: Hunan University of Science and Technology
Lu Xia: Hunan University of Science and Technology

Computational Economics, 2025, vol. 66, issue 1, No 28, 929-946

Abstract: Abstract For enterprises in the age of knowledge economy, innovation is an important manifestation of competitive advantage. The team is an important cornerstone of successful innovation. Team innovation activities are similar to group intelligence-inspired behaviors in that they also utilize information exchange and cooperation between groups to achieve innovation through simple and limited inter-individual interactions. Inspired by this, a team innovation optimization algorithm is proposed for the scientific research process based on group information sharing in team innovation in the article. Firstly, taking team innovation performance as the entry point, the Sigmoid function is employed as the individual performance growth rate, defining mutual iterative expressions for process input performance and outcome output performance, to realize a Team Innovation Optimization (TIO) algorithm with well-structured and highly scalable characteristics. The algorithm introduces chaotic mapping to enhance the innovativeness traversal of individual initialization, which makes the individual constrained by the local extreme value point decrease and improves the local optimization searching ability. The algorithm proposed in this paper has a smaller number of parameter settings and a simplified structure, which leads to a further increase in computational speed. Then, TIO is tested and compared with PSO, ACO, FA, BA and other algorithms by standard test functions. The experimental results show that the algorithm has good regulation ability and stability in finding the global optimum. Finally, the combination of TIO and ELM is used for cash flow small sample prediction, which overcomes the shortcomings of ELM model with high training accuracy and unsatisfactory generalization accuracy, ensures the accuracy of network optimization and convergence speed, and avoids the algorithm from falling into the phenomenon of local optimum, which is more effective.

Keywords: TIO; Sigmoid function; Cash flow; ELM (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-024-10728-9 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:kap:compec:v:66:y:2025:i:1:d:10.1007_s10614-024-10728-9

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-024-10728-9

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().