This page will be my portfolio!


**** Technical Analysis Indicator Strategy ****

•Buy-Low-Sell-High Strategy

•Support and Resistance Line Strategy

•Dual Moving Average Strategy

•Unmodified Turtle Strategy

•Turtle Strategy by Using Two Time Intervals

•A simple mean-reversion strategy by using Absolute Price Oscillator (APO)

•A simple mean-reversion strategy by using Absolute Price Oscillator (APO), and use standard deviation and simple moving average to dynamically adjust for changing volatility

•A simple trend-following strategy by using Absolute Price Oscillator (APO)

•A simple trend-following strategy by using Absolute Price Oscillator (APO), and use standard deviation and simple moving average to dynamically adjust for changing volatility





**** Time Series ****

• Check the time series stationarity through Augmented Dickey-Fuller Test on Tesla stock price

• Check the time series stationarity through calculating the hurst exponent on Tesla stock price

• A simplified pair traidng strategy by selecting stocks Adobe and Microsoft from 10 stocks based on cointegration and p-values, and gaining a neutral total position by making delta-neutral

• ** Update **: Use Cointegrated Augmented Dickey-Fuller Test (CADF) to check stationarity in the same pair

• Use Autoregression Integerated Moving Averages (ARIMA) to find out the seasonality of Amazon stocks and make a simple prediction for two years





**** Regression ****

• How to create trading conditions in Machine Learning and train the model

• Use Ordinary Least Squares (OLS) regression model to predict Amazon stocks and use R-sqaured, RMSE, and Sharpe Ratio to evaluate the prediction's performance

• Use K-Nearest Neighbors (KNN) Classification model to predict Tesla's stock price and use accuracy and sharpe ratio to evaluate the performance

• Use LASSO regression and Ridge regression to do regularization and shrinkage

• Use Support Vector Machine Classification (SVC) model to predict Apple's stock price and use accuracy and sharpe ratio to evaluate the performance

• Use Logistic Regression model to predict Apple's stock price, use accuracy and sharpe ratio to evaluate the performance and compare with the performence of SVC




**** Classification ****





**** Technical Analysis ****

•Simple Moving Average

•Exponential Moving Average

•Absolute Price Oscillator

•Moving Average Convergence Divergence (MACD)

•Bollinger Band

•Relative Strength Indicator

•Standard Deviation by Using Simple Moving Average

•Momentum





**** Risk Management ****

•A simple statistical arbitrage trend-following strategy by using the ratio of USD to 6 different currencies

•A measure of risk in trading by revisiting the dynamically adjusted volatility mean-reversion strategy ———— stop loss / max drawdown / positions limit / positions holding time / variance of PnLs / shapre ratio / sortino ratio / maximum executions per period / volume limits

•A static risk-managed mean-reversion strategy with adjusted volatility

•A dynamic risk-managed mean-reversion strategy with adjusted volatility





**** Data & Database ****

• A naive database in the form of hierarchical data format (HDF5)

• A simple relational databse by using PostgreSQL, save a pandas dataframe into a table, and read it back

• Build a securities master database for getting daily price update, and four tables: exchange, vendor, symbol, daily price

• Using requests and beautifulsoup to add S&P 500 stock symbols to MySQL database directly

• Getting historical price data for S&P 500 symbols from AlphaVantage

• Retrieving data from our database -- securities master





**** BackTesting ****

• A real clock simulator for checking data's timestamps

• A example showing how to use time value in order manager

• A dual moving average trading strategy which can connect to order book and order manager

• A simple for-loop backtesting on a dual moving average strategy

• A simple event-driven backtesting on a dual moving average strategy

• Building a perprtual series of Hong Kong Hang Seng Index Futures contracts for backetsting purpose





**** Trading System ****

Note: it is the first demo version of my trading system, only implemented in Python and Deques.

I gonna come back later to update it to C++ version with ordered data structures (e.g. trees) to improve the velocity.



• A simple liquidity provider simulator class with gateway to the limit order book

• A unit testing for the simple liquidity provider

• A simple limit order book using First-in-First-Out(FIFO) order

• A unit testing for the simple limit order book

• A simple arbitrage trading strategy with gateways from order books and order management

• A unit testing for the simple arbitrage trading strategy

• A simple order manager that sends orders and receives order from the gateways to market and trading strategy

• A unit testing for the simple order manager

• A simple market simulator that mimics the behaviors of market, receiving and filling orders, and rejecting questionable ones, from order manager

• A unit testing for the simple market simulator

• An overview of how the whole trading system works (event-driven backtester)

• A testing for the whole trading system