phynance Goto Github PK

01_tradingseries

algobot_eventbacktest_ibconnect_sqllite

This project aims to develop a comprehensive algorithmic trading engine that includes an event-driven backtesting framework, performance and risk metrics, and integration with Interactive Brokers for live trading. Additionally, it features an SQLite database to store completed trades, facilitating effective portfolio management.

competitive-data-science

Materials for "How to Win a Data Science Competition: Learn from Top Kagglers" course

double_bollinger_band_with_backtest

Backtest double bollinger band strategy on BTCUSD with Backtrader and QuantStats

face-recognition

Perform face recognition in video stream for registered members

hestonlmontecarlo-impliedvolsurfaceconstruction

simulation of Heston model by Monte-Carlo method

lgbm-regressor-in-g-research-crypto-forecasting-

it stores some of the common techniques used in Kaggle competition

lstm_timeseries_movement_prediction

Using LSTM to predict the moving direction of asset price in the next day

ml_from_scratch

Implementation of basic ML algorithms from scratch in python...

pca_portfolioconstruction

This project analyzes daily returns of S&P 500 stocks (2014-2019) using PCA to identify predictive statistical factors. We calculate regression coefficients via OLS, then long the 10 best-performing and short the 10 worst-performing stocks.

pricing-conditional-asian-option-mc-method-

pricing conditional Asian option by Monte-Carlo method with antithetic variate

stocks_pairtrading

Visa and Mastercard are taken as example of pair trading in this project. CADF test is implemented and Scaling-in strategy is used when investing the "spread".

time-series-maximum-drawdowns

Find and plot the multiple maximum drawdown in a time-series. The duration and extent of a drawdown is shown. Also, the recovery period is calculated and shown.