About us
The Thalesians are a group of dedicated professionals with an interest in Artificial Intelligence (AI) / Machine Learning (ML), quantitative finance, economics, mathematics, physics and computer science, not necessarily in that order. We currently run events London, New York, Budapest, Frankfurt and Prague!
Please also visit our main Thalesians web page here too to learn more about us!
The Thalesians are a member of Level39 - Europe's largest technology accelerator for finance, retail, cyber-security and future cities technology companies.
We consult, train, and write software. Our offering can be found on http://ai.thalesians.com/
Our GitHub page contains our open source Python financial analysis library PyThalesians.
If you are a full-time student, between jobs, or for any other reason would struggle with our Meetup dues, please let us know and we'll mark you as exempt from them!
Upcoming events
1
Hybrid Event: Alex Shkolnik - Portfolio Selection Revisited
140 W 62nd St, New York, NY, USIAQF & Thalesians Seminar Series: Portfolio Selection Revisited: Empirical Study 1975-Present. A Seminar by Alex Shkolnik.
6:00 PM Seminar Begins
7:30 PM ReceptionFordham University
McNally Amphitheater
140 West 62nd Street
New York, NY 10023Hybrid Event
Free Registration!
For Virtual Attendees: Please email web@iaqf.org for the link.Abstract:
In 1952, Harry Markowitz formulated portfolio selection as a trade-off between expected return and variance. This launched a massive research effort devoted to finding suitable inputs to mean-variance optimization. We show that PCA constructed Markowitz portfolios display highly counterintuitive properties as more securities are added. For example, the ratio of the true to the estimated portfolio risk grows without bound. We derive a correction formula that adjusts a PCA model in such a way that this ratio is stochastically bounded. These corrected Markowtitz portfolios also achieve zero variance asymptotically. We confirm these results via numerical simulations and test this theory further on a WRDS data set of U.S. Equity returns from 1975 to the present.Bio:
Alex Shkolnik is an Assistant Professor at the Department of Statistics and Applied Probability at the University of California, Santa Barbara and a Research Fellow at the Consortium for Data Analytics in Risk at the University of California, Berkeley where he was a postdoctoral scholar. Alex received his PhD in computational mathematics and engineering from Stanford University. His research interests include Monte Carlo simulation, high-dimensional statistics and quantitative financial risk management.11 attendees
Past events
454
