Chaotic Time Series Analysis

[vihan13singh]

• Abstract (2-3 lines)

Chaotic dynamical systems are everywhere (biology, society, stock market, weather, double pendulum) and most of them do not have an explicit dynamical equation and can be only understood through the available time series. The talk will discuss and demonstrate the various techniques employed to study chaotic time series data.

• Brief Description and Contents to be covered

• What is Chaos?
  • A dripping faucet...
  • The Prediction Company
  • Deterministic vs Random vs Chaotic
  • Sensitivity to Initial Conditions
• Analyzing Chaos
  • Dimensions
  • Lyapunov Exponents
  • Fourier Transform and Hilbert Transform
  • Attractor Reconstruction
  • Embedding Dimension
  • Time Delay
  • Mutual Information
  • Chaotic Data Sets
• Coding It Up
  • Working with real datasets
  • Analysis & Conclusions

• Pre-requisites for the talk
  Basic understanding of probability theory, statistics, calculus, matrix algebra, and ordinary differential equations. (will provide refreshers if the audience requires)

• Time required for the talk
  45-60 minutes

• Link to slides
  https://www.canva.com/design/DADuPClEstA/XvulZ6ToLWPHyCkzCYYjxw/view?utm_content=DADuPClEstA&utm_campaign=designshare&utm_medium=link&utm_source=sharebutton
  (still in the works, should be ready by 13th Jan)

• Will you be doing a hands-on demo as well?
  Nope.

• Link to iPython notebook (if any)
  Not yet...

• About yourself
  Vihan Singh is the Founder & CEO of Blackrose Technologies, a systematic trading firm focused on building black-box trading systems for the Indian financial markets. He's pursuing a Bachelor's in Mathematics & Computer Science from Ashoka University and co-authoring a biophysics research paper on mathematical modeling of protein folding.

• Are you comfortable if the talk is recorded and uploaded to PyData Delhi's YouTube channel?
  Yup.

• Any query?
  Nope.