Shihan Li

Mrs. Shihan Li

Fudan University
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 October 2021 in Algorithms
Verified
Journal Article
Open access
PDF file
Jianguo ZhengJianguo Zheng
Jianguo Zheng
YWYilin Wang
Yilin Wang
Shihan LiShihan Li
Shihan Li
HCHancong Chen
Hancong Chen
Accurate stock market prediction models can provide investors with convenient tools to make better data-based decisions and judgments. Moreover, retail investors and institutional investors could reduce their investment risk by selecting the optimal stock index with the help of these models. Predicting stock index price is one of the most effective tools for risk management and portfolio diversification. The continuous improvement of the accuracy of stock index price forecasts can promote the improvement and maturity of China’s capital market supervision and investment. It is also an important guarantee for China to further accelerate structural reforms and manufacturing transformation and upgrading. In response to this problem, this paper introduces the bat algorithm to optimize the three free parameters of the SVR machine learning model, constructs the BA-SVR hybrid model, and forecasts the closing prices of 18 stock indexes in Chinese stock market. The total sample comes from 15 January 2016 (the 10th trading day in 2016) to 31 December 2020. We select the last 20, 60, and 250 days of whole sample data as test sets for short-term, mid-term, and long-term forecast, respectively. The empirical results show that the BA-SVR model outperforms the polynomial kernel SVR model and sigmoid kernel SVR model without optimized initial parameters. In the robustness test part, we use the stationary time series data after the first-order difference of six selected characteristics to re-predict. Compared with the random forest model and ANN model, the prediction performance of the BA-SVR model is still significant. This paper also provides a new perspective on the methods of stock index forecasting and the application of bat algorithms in the financial field.

1 September 2007
Verified
Conference Paper
Closed access
Shihan LiShihan Li
Shihan Li
DQDePei Qian
DePei Qian
YLYi Liu
Yi Liu
JTJie Tong
Jie Tong
This paper presents an adaptive distributed TDMA slot assignment algorithm, called A-DRAND, which is an improved version of DRAM) in clustered wireless sensor networks where cluster heads need more slots and will be alternated afterwards by other cluster members for energy balance reason. It utilizes cluster info to allocate slots discriminately for different kind of sensor node and adapts its operation depending on the requirements of the application. The overhead is reduced significantly by reserving a special slot number range for slot reassignment. Simulation results show that running time and transmission cost of slot reassignment is only at most 1/m of that of all-participating assignment, where m is the proportion of cluster heads and other sensors with changing slots demanding in the network.

29 March 2023 in Digital Economy and Sustainable Development
Verified
Journal Article
Open access
PDF file
SCShiyi Chen
Shiyi Chen
Shihan LiShihan Li
Shihan Li
QLQingfu Liu
Qingfu Liu
CWChuanjie Wang
Chuanjie Wang
The FinTech development is expected to provide fertile soil for corporate digital transformation. Using the corporate digital transformation index creatively constructed in this paper, we verify that the development of regional financial technology can significantly promote corporate digital transformation, including digital technology and digital application. We find that the mechanisms mainly include easing financing constraints, improving the number and proportion of high-tech talents, and promoting enterprises to carry out more R&D activities. Further analysis shows that, the positive effect is more pronounced in private enterprises with better performance and lower capital expenditure. Our results provide evidence for the relationship between the financial sector and digital transformation.

18 July 2024 in Journal of Futures Markets
Verified
Journal Article
Closed access
Shihan LiShihan Li
Shihan Li
SLShuyao Li
Shuyao Li
QLQingfu Liu
Qingfu Liu
Yiuman TseYiuman Tse
Yiuman Tse

1 January 2023 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
YAYunbi An
Yunbi An
Shihan LiShihan Li
Shihan Li
QLQingfu Liu
Qingfu Liu
KZKaixin Zheng
Kaixin Zheng
This paper innovatively establishes the interrelationship between type I agency costs (conflicts between managers and shareholders) and type II agency costs (conflicts between controlling and minority shareholders). We further analyze the impact of agency cost interactions on the volatility of firm value. Then, we empirically test the hypotheses derived from our analysis using data on Chinese listed companies. We demonstrate that there exists an asymmetrically negative bi-directional causality between the two types of agency costs. Moreover, the negative interactions are moderated by the closeness of senior managers and board directors, state ownership, and various corporate governance mechanisms. Importantly, we show that intensified interactions smooth out the fluctuations of firm value.

1 March 2025 in Journal of Asian Economics
Verified
Journal Article
Closed access
Shihan LiShihan Li
Shihan Li
SLSi Li
Si Li
QLQingfu Liu
Qingfu Liu
XWXiao Wei
Xiao Wei