Light

seanbearden / stock-market-patterns Goto Github PK

View Code? Open in Web Editor NEW

0.0 1.0 0.0 10.94 MB

Researching trading patterns with AI, Machine Learning, and Data Science

License: MIT License

Python 0.81% Jupyter Notebook 99.19%

stock-market-patterns's Introduction

stock-market-patterns

Researching trading patterns with AI, Machine Learning, and Data Science

Initialize PostgreSQL Database

Install PostgreSQL on local machine:

 brew install postgresql
 brew services start postgresql@14

Create database with user and grant all privileges on database:

CREATE DATABASE your_dbname;
CREATE USER your_username WITH PASSWORD 'your_password';
GRANT ALL PRIVILEGES ON DATABASE your_dbname TO your_username;
\c your_dbname your_admin_user
-- You are now connected to database "your_dbname" as user "your_admin_user".
GRANT ALL ON SCHEMA public TO your_username;

run get_data.py to create tables and populate database.

Data gathering

run get_ticker_data.py to get historical daily candles from Alphavantage API.
run scrape_events.py to scrape earnings, dividends, and split dates and info from Finviz.

Packages

using a version of alpha_vantage from https://github. com/masonJamesWheeler/alpha_vantage/tree/intraday_monthly_update

stock-market-patterns's People

Contributors

Watchers

stock-market-patterns's Issues

Report on basic trend observations

probabilities of cloud trend reversals.
time horizons based on next monthly option expiration.
present in report

Handle delisted tickers

SGEN does not trade any longer, but the ticker remains in the ticker table. Need to add boolean field for delisted stock.

Explore tree models

Models:

Evaluation:

asymmetric loss
simple backtest

Bullish crossover when above the cloud

Create PostgreSQL database

install postgresql with homebrew on local machine
Create reference table for identifying ticker symbols
populate reference table
create table for daily stock quotes
populate daily stock quotes table
create tables for chart events: earnings, dividends, and splits
populate chart events tables
update README.md to outline how to setup PostgreSQL

bearish crossover when below the cloud

Given an Ichimoku Cloud signal, the target variable has a time-dependence that relates to the maximum length of the trade (position open to close). Determination of the time horizon is crucial for option trading.

Targets to explore:

max/min close in N days
The Ichimoku cloud projects into the future. Perhaps a classification problem could be of use to determine the likelihood the price will close above, within, or below the cloud, knowing where the cloud will be in N days.

Plots:

t-SNE
pairplot
correlation plot

Study for Ichimoku Cloud bounce

When overlaying Ichimoku clouds on price candles, there is an observed "cloud bounce" where the price enters the cloud, then retreats within the same day. I want to study the cloud bounce as a signal for option contract entry (put/call).

Setup:

Collect data from S&P 500. Use alphavantage.
Create Ichimoku cloud signals.

Basic:

Advanced:

Determine when the daily candle enters the cloud but closes outside of the cloud. Do not include instances where the price breaks through the cloud.
What is the correlation of high - close or close - low with price movement within N days.
When a cloud bounce occurs, what is the correlation of price movement with recent extremes? For example, if the bounce occurs far from a recent high/low, is the bounce likely to have a high price movement percentage?

Create table for quotes by minute

create stock_quotes_minutes
populate with recent data
update diagram in README.md

Create tables for technical indicators to speed up processing

Create tables for each technical indicator that is used often: SMA, MACD, RSI, MFI, RMI, Ichimoku clouds
Populate the table with standard parameters for technical indicators

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.