Information Theory & Predictive Analytics

on YouTube ↗46m

" summary

Introduces practical use of entropy = sum p log p to measure uncertainty (coin = 1 bit, fair die ≈2.6 bits, rigged die ≈0.7 bits) and uses penalize mutual information with momentum to force AI trading signals to deviate from pure momentum. Shows portfolio weighting by maximum entropy gives equal weights, uses mutual information to filter redundant alternative-data signals, and reports an options-listing pilot where honoring rare events cuts peak daily volume loss (several days causing ~90% of loss) down to under 20% and improves listing efficiency.

AI-written summary · about

" chapters (16)

1. 0:00Introduction
2. 1:07Why information theory
3. 3:55Rethinking event models
4. 6:44Defining entropy
5. 10:11Measuring uncertainty
6. 12:57Coin vs dice entropy
7. 17:11Conditional entropy
8. 19:40Entropy in finance
9. 22:30Three flavors of prediction
10. 25:37Mutual information game
11. 29:06Strategy analysis
12. 32:53Optimal guessing
13. 35:18Causality overrated
14. 39:10Rare events importance
15. 41:18Nasdaq pilot case
16. 44:26Summary and Q&A

" related talks

• 23mFalse Consensus, Information Theory, and Prediction MarketsYuqing Kong, Grant Schoenebeck · ITCS 2023
• 14mFair And Reliable Machine Learning For High-Stakes Applications:approaches Using Information TheorySanghamitra Dutta · Meet the Fellows Welcome Event
• 27mDetection and Estimation through an Information Theory LensSergio Verdú · Information Theory, Learning and Big Data (Simons Institute, 2015)
• 42mProbablyBart Massey · Open Source Bridge 2015
• 15mFundamental Limits Of Learning In Data-Driven ProblemsYanjun Han · Meet the Fellows Welcome Event
• 01h 11mStatistical Physics and Computation in High DimensionFlorent Krzakala, Lenka Zdeborova · Probability, Geometry, and Computation in High Dimensions Boot Camp (Simons Institute, Fall 2020)
• 37mAlgorithmic Fairness From The Lens Of Causality And Information TheorySanghamitra Dutta · Algorithmic Aspects of Causal Inference 2022
• 48mLearning by Local Entropy MaximizationRiccardo Zecchina · Random Instances and Phase Transitions (Simons Institute, 2016)