| Date |
Summary |
| 2019.8.7 |
- self-assessment
- syllabus
- using jupyter notebook (some tips to use jupyter notebook)
- programming basic
- computation model (CPU and memory)
- variables and naming
- simple data types (int, float, str)
- arithmetic operators (+-*/, //, %, **)
- first built-in data structure: list with slicing
- assignment operator (=), rational operators (<, ==, >), logical operators (and/or)
- selection (if-elif-else)
- iteration (for-in, while) with jump statements (break, continue, pass)
- application: Monte Carlo simulation, bisection method for root-finding
|
| 2019.8.10 |
- programming basic (cont'd)
- data structures
- list, tuple, dictionary, and set
- looping techniques: enumerate, zip, reverse, sorted
- list/dictionary/tuple/set comprehension
- functions
- user-defined function
- variable scope
- default arguments
- functional programming
- functional programming (map, filter)
- lambda expressions
- generator (yield)
- object-oriented programming
- class and object: ... in python, everything is an object.
- user-defined class: attributes and methods
- magic methods
- (single) inheritance and method overriding
- file I/O and with-as
- try-except-else-finally
- applications: file i/o, exceptions, datetime
- data processing
- data acquisition
- data crawlers (or you can buy financial data from those famous information suppliers)
- pandas: dataframe
|
| 2019.8.14 |
(no class due to personal excuse)
|
| 2019.8.17 |
- data processing (cont'd)
- data visualization
- using packages: matplotlib, seaborn, mpl_finance, pygal, bokeh
- technical analysis
- backtesting
- net present value
- maximum draw down (MDD)
- Sharpe ratio
|
| 2019.8.21 |
- numerical and scientific packages
- vectorization
- matrix computation
- interpolation
- optimization
- application: modern portfolio theory
- statistics
|
| 2019.8.24 |
- financial time series analysis
- multivariate linear regression: capital asset pricing model (CAPM), Fama-French 3-factor model
- autoregressive moving-average (ARMA) model
|
| 2019.8.28 |
- financial time series analysis (cont'd)
- generalized autoregressive conditional heteroskedasticity (GARCH) model
- vector autoregression (VAR) model
- cointegrated VAR using vector error correction (VEC) model
- stochastic processes
- random walk: geometric Brownian motion
- square-root and mean-reverting process: CIR model
- stochastic volatility model: Heston model
- jump-diffusion process: Merton's model
- option basics and pricing models
- valuation framework
- Monte Carlo simulation
- binomial option pricing model (BOPM)
- QuantLib tutorial
|
| 2019.8.31 |
- model calibration
- implied volatility
- CIR model
- Heston model
- risk management
- value at risk (VaR)
- dynamic delta hedging
|
| 2019.9.4 |
- machine learning tutorial
- regression with regularization: ridge regression & LASSO regression
- logistic regression
- support vector machine (SVM)
|
| 2019.9.7 |
- Granger causality: granger.ipynb
- machine learning tutorial (cont'd)
- decision tree and random forest
- principal component analysis (PCA)
|
| 2019.9.11 |
- machine learning tutorial (cont'd)
- k-means clustering
- reinforcement learning: Q-learning
- performance issues
- row major vs. column major
- performance profiling
- multiprocessing/multithreading and Amdahl's law
- dynamic compiling
|