FinTech Intelligent Recommendation Systems for Crowdfunding Success

Citation Author(s):
YUNFENG
WANG
Universiti Teknologi Malaysia
Submitted by:
YUNFENG WANG
Last updated:
Sat, 02/01/2025 - 00:32
DOI:
10.21227/55hx-h931
License:
Creative Commons Attribution
3 Views
Categories:
Other
Keywords:
Crowdfunding、Machine Learning、Predictive Analytics、Random Forests、Visual Analytics、Social Networks
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

In China’s evolving FinTech ecosystem, intelligent recommendation systems have become pivotal for enhancing crowdfunding outcomes. This study integrates the Information Systems Success Model, Dynamic Capabilities Theory, Signaling Theory, and Trust Theory to examine how such systems shape crowdfunding success. Adopting a positivist and quantitative approach, data were collected from 302 users of Chinese crowdfunding platforms employing intelligent recommendation engines. Structural Equation Modeling (SEM) results indicate that system quality, information quality, signaling, trust, and user engagement significantly boost project financing outcomes, while social influence further moderates these effects.In terms of optimizing the design and governance of intelligent recommendation systems for crowdfunding success, a deeper understanding among platform developers and policymakers was sought through the importance-performance matrix analysis (IPMA). The results of IPMA can help identify strategic focus areas for optimizing system features, strengthening trust, and matching projects with investors more effectively, thereby enhancing crowdfunding viability within China’s unique FinTech ecosystem.

Instructions: 

The dataset (Raw Data.xlsx) contains survey responses from 302 users of Chinese crowdfunding platforms, primarily used for Structural Equation Modeling (SEM) and Importance-Performance Matrix Analysis (IPMA). It includes demographic information (gender, age, education, investment experience), independent variables (system quality, information quality, signaling mechanisms, trust, and user engagement), dependent variable (crowdfunding success), and moderating variable (social influence). All variables are measured using a 5-point Likert scale (1 = Strongly Disagree, 5 = Strongly Agree). Data analysis involves data cleaning, descriptive statistics, Confirmatory Factor Analysis (CFA), followed by SEM and IPMA using SmartPLS to evaluate the impact of intelligent recommendation systems on crowdfunding success.

 

The document includes the theoretical background, literature review, research model, methodology, data analysis, and discussion, focusing on how FinTech-driven intelligent recommendation systems enhance crowdfunding success. The study integrates the Information Systems Success Model (ISSM), Signaling Theory, Trust Theory, and Dynamic Capabilities Theory to examine the influence of system quality, information quality, signaling, trust, and user engagement on crowdfunding outcomes. The methodology details data collection (500 questionnaires distributed, 302 valid responses) and measurement variables (SEM modeling), while the results section employs SEM to test hypotheses and IPMA to identify key areas for improvement, providing strategic insights for platform developers and policymakers.

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?