sey-kh

## gru_recurrent_network.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                sey-kh
                / gru_recurrent_network.md
            
            
              Last active
              June 11, 2019 07:05
            
              
                GRU recurrent network
              
          
    GRU recurrent neural network

GRU (Gated Recurrent Unit) aims to solve the vanishing gradient problem (The problem is that in some cases, the gradient will be small, effectively preventing the weight from changing its value then the network stop learning) which comes with a standard recurrent neural network.
Standard recurrent neural network


RNN network can predict output base on previous output or predict output by taking external input + previous output. It kind of ilterate process by taking previous output to generate new output in terms of processing sequence data.
As above diagram mentioned, there are external input (I0, I1, I2) and sequence output (O0, O1, O2)

  
## summary_of_getting_started_quantopian_v1.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                sey-kh
                / summary_of_getting_started_quantopian_v1.md
            
            
              Last active
              June 7, 2019 13:48
            
              
                Summary of Getting Started - Quantopian
              
          
    Lesson 2 Data exploration

Research environment enable us to query pricing, volume and returns data for 8000+ US equity from 2002 up to the most recently completed trading day.
We need to specify start and end date so that it will return a Data frame indexed by date.
Alternative Data

Algorithm trading is an information advantages, the whole reason that we come up with an economic hypothesis is to come up with statistical edge or
some piece of information that we can glean from the data that other people don't have yet.

  
## summary_of_getting_started_quantopian_v0.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                sey-kh
                / summary_of_getting_started_quantopian_v0.md
            
            
              Last active
              June 7, 2019 09:07
            
              
                Summary of Getting Started - Quantopian
              
          
    Lesson 2 Data Exploration


Uses a data pipeline to query stocktwits and returns data, and plots the results for AAPL

While making pipeline we can inspecting the message volume and sentiment score (bull minus bear) columns from the stocktwits dataset
Pipline execution and Filter results

sentiment score (bull minus bear)

bullish means: expecting a stock to rise in value