Search results

This study aims to tackle the critical issue of detecting stock market manipulation, which undermines the integrity and stability of financial markets globally. Even enhanced with machine learning, traditional statistical methods often struggle to analyze high-frequency trading data effectively due to inherent noise and the limited availability of publicly known manipulation cases. This leads to poor model generalization and a tendency toward over-fitting. Focusing on China's securities market, our study introduces an innovative approach that employs deep learning-based high-frequency jump tests to overcome these challenges and to develop a more effective method for identifying manipulative activities.

We employed the “Jump Variation – Time-of-Day” (JV-TOD) non-parametric technique for jump tests on high-frequency data, coupled with the synthetic minority over-sampling technique (SMOTE) algorithm for re-balancing sample data. Our approach trains a deep neural network (DNN) on refined data to enhance its ability to identify manipulation patterns accurately.

Our results show that the deep neural network model, calibrated with high-frequency price jump data, identifies manipulation behavior more specifically and accurately than traditional models. The model achieved an accuracy rate of 94.64%, an F1-score of 95.26% and a recall rate of 95.88%, significantly outperforming traditional models. These results demonstrate the effectiveness of our approach in mitigating over-fitting and improving the robustness of market manipulation detection.

The proposed model provides regulatory entities and financial institutions with a more efficient tool to monitor and counteract market manipulation, thereby improving market fairness and investor protection.

By integrating the JV-TOD jump test with deep learning, this study proposed a new approach to market manipulation detection. The innovation is in its capacity to detect subtle manipulation signals that traditional methods typically overlook. Our model, which is trained on jump test data enhanced by the SMOTE algorithm, excels at learning complex manipulation patterns. This enhances both detection accuracy and robustness. In contrast to existing methods that are challenged by the noisy and intricate nature of high-frequency data, our approach shows enhanced performance in identifying nuanced market manipulations, offering a more effective and reliable method for detecting market manipulation.

The information used for supervision by regulatory departments in public-private partnership (PPP) projects is primarily transmitted and processed by the PPP implementation department, which negatively impacts the information quality, leading to information asymmetry and undermining the overall effectiveness of supervision. This study aims to explore how to use blockchain to anchor the information used for supervision in PPP projects to the original information, to strengthen the oversight.

This paper adopts the principles of design science research (DSR) to design a conceptual framework that systematically organizes information along the information dissemination chain, ensuring the reliable anchoring of original information. Two-stage interviews involving experts from academia and industry are conducted, serving as formative and summative evaluations to guide the design.

The framework establishes a weak-centralized information organizing mode, including the design of governance community and on-chain and off-chain governance mechanisms. Feedback from experts is collected via interviews and the designed framework is thought to improve information used for supervision. Constructive suggestions are also collected and analyzed for further development.

This paper provides a novel example exploring the inspirations blockchain can bring to project governance, like exercising caution regarding the disorderly expansion of public sector authority in addressing information disadvantages and how to leverage blockchain to achieve this. Technical details conveyed by the framework deepen understanding of how blockchain benefits and the challenges faced in successful implementation for practitioners and policymakers. The targeted evaluation serves as rigorous validation, guiding experts to provide reliable feedback and richer insights by offering them a more cognitively convenient scenario.