About
Quantitative AI Researcher ยท PhD, MMLab CUHK
Building end-to-end AI investment systems.
I work on deep learning systems for active investing, adaptive factor modeling, market regime detection, and event-driven trading. My work connects academic research with deployable quantitative investment systems across Chinese equity markets and global markets.
Research
End-to-end active investing, online adaptive factor models, event-driven trading, and financial knowledge graphs.
Live Investment
Practical AI quant systems for A-share and overseas markets, spanning signals, backtesting, and portfolio construction.
Collaboration
Open to research, client, and investment collaboration around end-to-end AI quantitative investment systems.
About
Zikai (Nathaniel) Wei is a quantitative AI researcher focused on end-to-end investment systems. He earned his PhD in Information Engineering from The Chinese University of Hong Kong (2023), where he trained at the Multimedia Laboratory (MMLab) under Prof. Xiaoou Tang and Prof. Dahua Lin.
He works closely with Prof. Jian Guo on next-generation quant AI, including event-driven trading, financial knowledge graphs, and large-scale adaptive factor models. His industry experience spans a top-tier asset management firm in mainland China and a top-tier hedge fund in Hong Kong, with practical work on live quantitative investment systems.
His research includes pioneering end-to-end active investing (E2EAI), the online adaptive factor model HireVAE (IJCAI 2023), and co-first-author work on end-to-end event-driven trading (Janus-Q).
Collaboration & Investment
My team and I work on live AI-driven quantitative investment strategies across Chinese equity markets and global markets, based on end-to-end AI investment systems. We welcome conversations with institutional clients, investors, and research collaborators interested in systematic strategies, data-driven portfolio construction, and deployable AI investment systems.
We can also discuss customized strategy development for different mandates, markets, risk preferences, and investment horizons.
For collaboration or investment inquiries, please contact me.
Mentorship
I also serve as an external mentor for students and research teams from universities in the Greater Bay Area, especially for projects related to AI for finance, quantitative investment, deep learning, and real-world investment system development.
End-to-end deep learning for active investing.
IJCAI 2023 HireVAEOnline adaptive factor modeling with regime-switching VAE.
arXiv 2026 Janus-QEnd-to-end event-driven trading via hierarchical reward modeling.
Internship Opportunities
I am open to recruiting interns interested in building AI investment systems: data pipelines, factor and regime modeling, event-driven signals, and end-to-end strategy research and backtesting. Strong Python/PyTorch skills and interest in quantitative finance are welcome. Please contact me to discuss opportunities.