Derivatives Analytics with Python & Numpy
summary
Prototype claims that Python with NumPy and pandas runs production-grade derivatives analytics: Monte Carlo with least-squares Monte Carlo regression, variance reduction by antithetic paths and moment matching, and arrayized simulation. A concrete result shows 25 time steps and 35,000 paths in 1.5s (180 MB), and 50 steps with 100,000 paths (~1 GB) in 8.5s—about a 480× speed gain over a naïve C/C++ implementation that took “dozens of minutes.” Result is delivered as a web service with optional on‑premise install.
AI-written summary · about
chapters (15)
- 0:00Start
- 1:41Background in Business Administration
- 2:59Topics
- 5:07Typical Tasks in the Context of Derivatives Analytics
- 6:17Why Python
- 7:58The Financial Market
- 9:37Time Series
- 11:41Plot Things in 2d and 3d
- 15:41Cross-Section Data
- 23:17Index Level Path Generation
- 25:14Python Usage for Monte Carlo Simulation
- 26:59Monte Carlo Simulation
- 28:07The Optimal Stopping Problem
- 38:00Variance Reduction
- 53:59Preferred Data Type
related talks
45mInteractive Analysis of (Large) Financial Data Sets
01h 18mKeynote
29mMonte Carlo Business Case Analysis with pandas
28mDerivations, Not Just Simulations: Teaching Applied Mathematics with Scientific Python
33mWhy Python Has Taken Over Finance
22mSupercharge Scientific Computing in Python with Numba
39mAccelerated Data Science Libraries
42mUsing Python pandas for scientific Research