))
Mark Kritzman on Relevance-Based Prediction, An Alternative to Machine Learning
Fetch error
Hmmm there seems to be a problem fetching this series right now.
Last successful fetch was on July 26, 2024 20:36 (
What now? This series will be checked again in the next hour. If you believe it should be working, please verify the publisher's feed link below is valid and includes actual episode links. You can contact support to request the feed be immediately fetched.
Manage episode 421471367 series 3557118
İçerik CFA Institute Research Foundation tarafından sağlanmıştır. Bölümler, grafikler ve podcast açıklamaları dahil tüm podcast içeriği doğrudan CFA Institute Research Foundation veya podcast platform ortağı tarafından yüklenir ve sağlanır. Birinin telif hakkıyla korunan çalışmanızı izniniz olmadan kullandığını düşünüyorsanız burada https://tr.player.fm/legal özetlenen süreci takip edebilirsiniz.
Mark joins host Lotta Moberg to discuss relevance-based prediction, a transparent and adaptive alternative to machine learning.
Mark Kritzman, CFA is a Founding Partner and CEO of Windham Capital Management, LLC. He is also a Founding Partner of State Street Associates, and he teaches a graduate finance course at the Massachusetts Institute of Technology.
Mark served as a Founding Director of the International Securities Exchange and as a Commissioner on the Group Insurance Commission of the Commonwealth of Massachusetts. He also served on the Advisory Board of the Government Investment Corporation of Singapore (GIC) and the boards of the Institute for Quantitative Research in Finance, The Investment Fund for Foundations, and State Street Associates.
He is currently a member of the Advisory Board of the MIT Sloan Finance Group, the Board of Trustees of St. John’s University, the Emerging Markets Review, the Journal of Alternative Investments, the Journal of Derivatives, the Journal of Investment Management, where he is Book Review Editor, and The Journal of Portfolio Management.
Relevance-based prediction is a new approach to data driven forecasting which serves as a favorable alternative to both linear regression analysis and machine learning. In this episode, Mark Kritzman, one of the leading researchers in this field, joins us to discuss the seminal scientific innovations underlying this approach to predictions, namely the Prasanta Mahalanobis’ distance measure and Claude Shannon’s information theory.
We also discuss the three key tenets of relevance-based prediction, that of relevance, which measures the importance of an observation to a prediction, fit, which measures the reliability of each individual prediction task, and codependence, which holds that the choice of observations and predictive variables should be determined jointly for each individual prediction task. Get ready for a highly educational, stimulating, and demanding episode!
To review Mark's work for yourself, use the links below:
JOIM paper (Relevance)
JFDS paper (Relevance-Based Prediction)
To purchase a copy of his book, use the links below:
https://www.predictionrevisited.com/
https://www.wiley.com/en-us/Prediction+Revisited%3A+The+Importance+of+Observation-p-9781119895596
Financial Thought Exchange is the official podcast and video channel of the CFA Institute Research Foundation. If you would like to support the show and our work, please donate here: https://rpc.cfainstitute.org/en/research-foundation/donate
15 bölüm
Paylaş
