Skip to content

Testing multiple models on the time series data for stock price prediction

Notifications You must be signed in to change notification settings

lhmtrinh/Quantative_Models

 
 

Repository files navigation

  1. dividend yield talks about price changes directly as this can be taken as inverse price to dividend ratio
  2. stock-bond correlation
    1. Bond and equity prices reflect the discounted value of their future cash flows, where the discount rate approximately equals the sum of a:
    2. Real interest rate – compensation for the time value of money
    3. Inflation rate - compensation for the loss of purchasing power over time
    4. Risk premium – compensation for the uncertainty of receiving future cash flows

compare the fitting vs overfitting denoising using the autoencoder kalman filter seperating the signal from noise

irrespective of the activation function, applying pooling on the

drop out layers help in creating subgraph and model averaging kind of concepts information coefficient bayesian inferance prior psoterior granger causality

Data Ingestion - Data Splitting for validation and Data Preprocessing - Denoising AutoEncoder - Kalman Filter - Dimensional Reduction

Model: - Training Strategies - Cross Validation - Trading strategies - Supply shock - Causality, find the casual dimension - - LOSS Functions - Optimizer choice - Learning Rate scheduler

Plotting Data in everyphase

clustering the

not too much position sizing and all the other volatality into consideration

About

Testing multiple models on the time series data for stock price prediction

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%