I am a researcher specializing in corporate finance and fintech, with a particular focus on insider trading, green finance, and blockchain technology. With recent advancement in AI, financial institutions and regulators are increasingly leveraging AI-based technologies to further automate their operations. By leveraging real-time big data, AI is revolutionizing a variety of financial domains from algorithmic trading and portfolio management to cybersecurity and fraud detection, risk management, regulatory compliance, all the way to customer services. Witnessing this massive shift in finance fueled my curiosity as a PhD student, motivating me to explore how AI can address my research questions while developing my expertise in ML, which is the core of AI systems. This interest has guided my dissertation focus, where I employed advanced ML and causal inference methods to uncover intricate patterns and rigorously test challenging hypotheses within the domains of my interest.
In particular, I research on what the key determinants of insider trading are and how ML can help better identify these factors. By uncovering the key factors predicting insider trading behaviors, firms can proactively implement accurate measures to comply with regulatory requirements and ensure transparency in their trading activities. More importantly, understanding these predictors helps regulators develop more robust algorithms and systems to detect and prevent insider trading in real-time, ensuring timely intervention and enforcement of regulatory standards. Lastly, predictive models derived from such research can inform investment decisions, aid in portfolios management, and optimize trading by leveraging insights into insider behaviors. This research along with over half a decade of industrial experience in financial markets has exposed me to a variety of fintech innovations and applications. By joining academia as a faculty, I am committed to contributing meaningful insights to this field after graduation and look forward to collaborating with esteemed colleagues and talented students to advance our understanding and push the boundaries of knowledge in finance.
My doctoral dissertation examines the efficacy of ML techniques in predicting insider trading. Using advanced approaches such as Bayesian optimization for model hyperparameter tuning and SHAP value analysis for feature importance assessment, I identified crucial factors influencing insider trading activities. The results indicate that ML models, particularly XGBoost and Random Forest, surpass traditional methods like logistic regression in their predictive accuracy for insider trading. The study delves into the intricate dynamics of insider trading decisions, emphasizing the significance of both individual-level traits and firm-specific characteristics. Notably, it highlights insider compensation structure as a predominant determinant of insider trading behavior, overshadowing factors such as age, tenure, and gender among insiders. Additionally, the research reveals that ML models exhibit superior predictive capability for trading behaviors among female insiders and those from the Silent Generation. These findings underscore the role of ML in enhancing the predictability of insider trading patterns, offering valuable insights for stakeholders and advancing the broader application of ML within the finance domain.
During my MBA program, I co-authored a book titled “An Introduction to Stock Market Indices”, which was published by the Securities Exchange Organization in Tehran. This comprehensive work aimed to raise readers’ awareness of various types of capital markets and their computational methods across five detailed chapters. Additionally, I have authored a paper titled “Corporate Social Responsibility (CSR) and Firm Value: International Evidence from the Announcement of Dividend Omission and Reduction”, which was presented at the Southern Finance Association in 2022. This study investigates the impact of CSR activities on firm value during dividend omission and reduction announcements to answer how investors respond to firms’ CSR activities during crises. Our findings suggest a negative relationship between CSR investment and cumulative average returns (CAR), which is aligned with agency theory’s view of CSR as a managerial agency problem and a potential waste of corporate resources. However, we also discovered that firms with established CSR practices exhibit greater resilience during crises, supporting theories of effective corporate management.