Improved Decision Making with Pareto Fronts
summary
Claims that Pareto fronts expose the set of non‑dominated tradeoffs so no precommitted weighting is needed, and that holding subjective choices until after exploration improves decisions. Builds a web pareto app and shares Jupyter notebooks and a deep prototyping module for hands‑on work. Uses machine learning to map sequence → binding in a labgenius drug‑discovery pipeline and cites a donorschoose case where multi‑objective search yields an absolute 5% drop in misclassification and ~8% relative cut in false positives. Recommends genetic algorithms for huge decision spaces.
AI-written summary · about
chapters (5)
- 0:00Start
- 9:20Single Objective Optimisation
- 11:23Subjectivity
- 20:37DNA Assembly to Protein Function
- 21:55Case Study - Protein Design
related talks
33mA Hands-On Introduction To Multi-Objective Optimization
12mCausal Inference And Data-Driven Decision-Making
01h 28mBayesian Decision Analysis [Tutorial]
02mThe Missing Piece
25mExploring Tradeoffs in Experiment Management as part of AI Platforms
29mDecision sciences in Python
09mTowards Credible and Effective Data-Driven Decision-Making
15mUnderstanding Decisions Driven by Big Data