OpenTalks.AI - Андрей Устюжанин, Предиктивная аналитика - обзор текущего состояния и что произошло важного за 2019 год

Transcript

1. Предиктивная аналитика: тренды, технологии и точки роста. Частный взгляд. 21 Feb, 2020, Opentalks.ai Andrey Ustyuzhanin
2. Quick self-intro Andrey Ustyuzhanin 2 ▌ Head of LAboratory of Methods for Big Data Analysis, LAMBDA at HSE ▌ Head of Yandex School of Data Analysis team at LHCb and SHiP at CERN › Applications of Machine Learning to natural science challenges › Playground for advanced methods and technologies ▌ Co-organizer of several data science competitions (Flavours of Physics, TrackML, IDAO) ▌ Education (MLHEP, ICL, ClermonFerrand, URL Barcelona, Coursera) ▌ Core expertise: › Data analytics, simulation, generative models, complex optimization ▌ Industry predictive analytics projects with “YADRO”, “MMK”, “Yandex”
3. Predictive analytics – how to turn data into future insights. Andrey Ustyuzhanin 3 https://wisdomschema.com/analytics-capability-maturity/
4. Andrey Ustyuzhanin 4 https://www.ringdna.com/blog/periodic-table-predictive-analytics
5. http://bit.ly/39JgqFc See Emeli’s talk for examples
6. Predictive Analytics Key Drivers ▌ Transition from analog to digital › IOT – data abundance › Dataism – mindset, developed by significance of Big Data (flows) ▌ Global AI race › AI technologies transit from ‘nice to have’ to ‘must have’ for companies and governments › Changing nature of power ▌ Sustainable solutions, service personalization › From offline to real-time › “What-if … “ analytics, process-oriented analytics Andrey Ustyuzhanin 6
7. Big Data Problem ▌ Complexity of the system › Data pieces are always missing › Noise to signal ratio may get high › No single expert knowledge ▌ Process-agnostic › Data is only part of the truth › Relying on part of the past we cannot predict all future scenarios › Future could be a very special version of the past Andrey Ustyuzhanin 7
8. Data is great, but is it the final answer? Andrey Ustyuzhanin 8 http://bit.ly/2T4YNJv
9. Data-driven version of the future Andrey Ustyuzhanin 9 http://bit.ly/2T4YNJv
10. Simulation Andrey Ustyuzhanin 10 • add any additional rules from experts • build a trustworthy model of the system, including those rough edges that your data might miss • build and verify models with historical data • replay it with slightly different conditions and random variations • take into account unexpected interactions (think butterfly effect) http://bit.ly/2T4YNJv
11. Simulation toolkits ▌ Anylogic ▌ NetLogo ▌ Flexsim ▌ Simio, ▌ Simul8 ▌ Arena ▌ Salabim ▌ Hash.ai Andrey Ustyuzhanin 11
12. Simulation for industry – Digital Twins Reduced CO emission by factor of 3.5 by CompMechLab, http://bit.ly/37DPl4Y Andrey Ustyuzhanin 12 DOI 10.1109/ACCESS.2018.2890566 Optimisation of: ▌ Design ▌ Logistic ▌ Supply chain ▌ New materials Testing of ▌ Maintenance ops ▌ Anomaly ▌ “What-if” scenarios http://bit.ly/2SJfTNO
13. Optimisation based on simulations Andrey Ustyuzhanin 13 http://bit.ly/2V9iXo0 http://bit.ly/32eK3fi https://arxiv.org/abs/2002.04632
14. Simulation in Science (Particle Physics) ▌ Toolkits: › Pythia › GEANT4 ▌ Applications: › Rare events simulation › Background process › Tuning of software › Design of hardware Andrey Ustyuzhanin 14
15. Interesting Questions to Explore ▌ Simulation speed-up by either solving ODEs or approximating routine simulator calls by Neural Nets, arXiv:1812.01319v2 ▌ Transfer Learning for Machine Fault Diagnosis, http://bit.ly/37PYCal , http://bit.ly/2T4qT7l ▌ Optimisation of computationally expensive hardware design https://arxiv.org/abs/2002.04632 ▌ Tuning of heavy simulators to match historical data Simulation of realistic anomalies - https://arxiv.org/abs/1912.00520 ▌ Fast simulation of physics process by neural networks https://arxiv.org/abs/1903.11788 Andrey Ustyuzhanin 15
16. Key technologies towards Prescriptive Analytics › Simulation, Simulation tuning, Simulation speed-up › Transfer Learning (from another domain, from prior knowledge) › NLP (Process Mining, Network Analysis) › Extrapolating models, causality › Interpretability, uncertainty modelling › Few-shot learning (see talk of Sergey Bartunov) Andrey Ustyuzhanin 16
17. NLP+Analytics. ThoughtSpot Andrey Ustyuzhanin 17 https://www.thoughtspot.com/
18. NLP: Automated paper parsing Andrey Ustyuzhanin 18
19. AI Physicist concept Andrey Ustyuzhanin 19
20. AI Physicist concept++ Andrey Ustyuzhanin 20
21. Dream come true Andrey Ustyuzhanin 21
22. Conclusion ▌ Predictive Analytics (PA) is a multifaceted and ubiquitous technology ▌ Data-driven PA is not enough ▌ PA is going to expand/adapt a variety of new aspiring technologies ▌ … while pushing AI quite far: › Man-in-the-loop learning › Advanced simulation › AI “scientist” › Few-shot learning ▌ Scientific collaborations (e.g. with CERN, SKA) serve as a great testbed for future industry cases Andrey Ustyuzhanin 22 http://cs.hse.ru/lambda/ anaderiRu@twitter austyuzhanin@hse.ru