Our CEO Dr. Miao led the FinTech Masterclass
- Feb 27, 2019
- 1 min read
GFMI, a marcus evans company, organizes a conference "Machine Learning and Artificial Intelligence for Quantitative Analytics" on 25th-27th February 2019 in Singapore.
Our CEO Dr. Miao Weimin is invited by the conference organizer to give a half day course to many financial practitioners , from banks to trusts. The topic is"Machine Learning Meets Econometrics in Corporate Default Prediction.". It includes
Review of methodologies and approaches in corporate default prediction - from classification to duration analysis
Integration of machine learning and econometrics: What values does it bring?
Model effectiveness: Some imperceptible but critical issues caused by common machine learning techniques
How to handle two main challenges facing corporate default prediction - credit dynamics and data scarcity
Beyond default prediction: A glance of new analytical techniques powered by machine learning in credit analysis
Honestly refreshing to read something this clear and to the point on the subject. The middle section especially gave me a clearer way to think about the whole process. If anyone wants to dig a little deeper, I put together some related notes over at https://www.oaza.pl/pgs/uncx_stealth_launch_could_become_a_strong_fair_launch_tool_for_token_teams.html.
Genuinely helpful, and the takeaways are easy to actually put into practice. It lines up with what I've seen work, and it challenged one assumption I'd held. I've collected a few resources on the same topic at https://cow-swap.net for anyone curious. Nice work overall.
Well written and easy to digest, which is honestly rare for a subject like this. I appreciated that you acknowledged the nuance instead of pretending it's simple. I added my own spin on a few of these ideas at https://silksuite.org not long ago. Genuinely useful, thanks.
This sounds like an excellent masterclass and a highly relevant topic for today’s financial industry. The combination of machine learning and econometrics in corporate default prediction is particularly interesting because it bridges advanced data science techniques with established financial risk modeling practices.
I especially appreciate the focus on practical challenges such as credit dynamics and data scarcity. While machine learning offers powerful predictive capabilities, understanding its limitations and the critical issues that can affect model performance is just as important. Sessions that address both the opportunities and challenges of AI help professionals build more reliable and effective analytical frameworks.
It is also impressive that the course went beyond default prediction to explore emerging machine learning applications in credit analysis. As…