The informatization of cities has been further promoted, and the construction of smart cities supported by technological innovation has been upgraded. The financial industry and data are closely related. Whether the financial industry can make good use of new information technology is the key to its successful transformation. The development of smart cities has a significant effect on the development of people’s livelihood, the process of urbanization, the use of technology, the solution of urban problems, and the improvement of economic levels. This also provides a good choice for the development of cities in each country. For better development, it needs technical support. Therefore, it is very important to improve the technical level. This research mainly discusses the risk assessment and regulation algorithms of financial technology platforms in smart cities. This study divides the risk decision channels into two paths based on the smart city theory, considers the internal risk factors and external risk factors of the robo-advisory service platform from the three perspectives of platform characteristics, corporate characteristics, and investor characteristics and exploring the construction of a robo-advisory service platform risk prediction model based on the machine learning perspective. The design and implementation of a personalized financial investment prototype system, a Python-based web development framework Django, and a variety of toolkits have realized a B/S architecture robo-advisor. Among them, the function of buying and selling ETF and the trend recording function after buying are realized by simulating the transaction data collected by the data collection module. The study found that the key potential characteristics that constitute platform risks are mainly the listing year of the background company, the age of the platform, the investment threshold, and the search index. To a certain extent, this provides data support for investors and regulatory authorities to evaluate platform capabilities and platform selection. Investors should comprehensively consider platform qualifications when making platform decisions and pay attention to information such as the age of listing of companies with platform background, platform age, and investment thresholds. Only when the quality of people is improved, the quality of the population of this city improves, so that the development of the city has a broad room for growth. The accuracy of the similar formula calculation method in the big data proposed in this study reached 88%. This research provides new ideas for perfecting the black box regulatory system of robo-advisory algorithms.
展开▼
