Stock Extractor library
Project description
Stock Prediction Pipeline
Step 1 - Build Stock Database
Step 2 - Normalize Stock Data
Step 3 - Build Features and Visualization
Step 3 - Build Prediction Models
Metrics
The metrics of prediction models should be based on profits and loss they give.
-
Profit vs. loss
-
Backtest
Stock data
Collected stock data include following values:
- Close
- Open
- High
- Low
- Volumn
- Change
- Percentage Change
Derivative values:
- Return
- Alpha
- Volatility
- Alpha*
- Sharpe
Business Taxonomy
There is a large number of companies in stock market. It is crucial to take a look over their financial reports and market indices to have a correct view of the companies' business status.
In this section, we want to build several main groups of companies. Each group represents the area of business that the company is taking part in. In addition, we target to give a common credit score for each group, and also the rank of company in that group.
-
Input:
- Stock indices
- Companies financial reports
-
Output:
- We want to have a comparison between the areas and give the advice on which business we should invest in.
- We want to have a table that ranks companies and shows their potential in market.
Installation:
conda create --name eagle python=3.7
conda activate eagle
pip install -r requirements.txt
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
Hashes for eagle_kaist-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 13324f7d568546fc663a617fff3409c229f732cfbc89c77830afe69ca7c5c732 |
|
MD5 | 6f6d1177f729e5ff0e90a1883dbec04b |
|
BLAKE2b-256 | eded3d5fd60752c3d9a98bcf69b1175274a5ce149a4e83ad599b14eed2940a98 |