Risk Assessment and Regulation Algorithm for Financial Technology Platforms in Smart City

Area of Science:

• Financial Technology (FinTech)
• Smart City Development
• Risk Assessment and Regulation

Background:

• Smart city initiatives increasingly rely on technological innovation, impacting urban development and economic growth.
• The financial industry's transformation hinges on effectively leveraging new information technologies.
• Robo-advisory platforms are integral to modern financial services, necessitating robust risk management strategies.

Purpose of the Study:

• To discuss risk assessment and regulation algorithms for financial technology platforms in smart cities.
• To explore the construction of a risk prediction model for robo-advisory service platforms using machine learning.
• To provide data support for investors and regulatory authorities in evaluating platform capabilities and selection.

Main Methods:

• Divided risk decision channels into two paths based on smart city theory.
• Considered internal and external risk factors from platform, corporate, and investor perspectives.
• Developed a B/S architecture robo-advisor prototype using Python/Django and machine learning for risk prediction.

Main Results:

• Identified key risk factors: background company listing year, platform age, investment threshold, and search index.
• Achieved 88% accuracy in risk prediction using a novel big data calculation method.
• The developed system simulates ETF trading and trend recording.

Conclusions:

• Investors should consider platform qualifications, company listing age, platform age, and investment thresholds.
• The findings offer new insights for refining the regulatory system for robo-advisory algorithms.
• Improving the technical level and data utilization is crucial for financial technology platforms in smart cities.