All Projects → hardyqr → Cnn For Stock Market Prediction Pytorch

hardyqr / Cnn For Stock Market Prediction Pytorch

CNN for stock market prediction using raw data & candlestick graph.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Cnn For Stock Market Prediction Pytorch

okama
Investment portfolio and stocks analyzing tools for Python with free historical data
Stars: ✭ 87 (+1.16%)
Mutual labels:  finance, time-series
Tsai
Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai
Stars: ✭ 407 (+373.26%)
Mutual labels:  time-series, cnn
Atspy
AtsPy: Automated Time Series Models in Python (by @firmai)
Stars: ✭ 340 (+295.35%)
Mutual labels:  time-series, finance
Kaggle Competition Favorita
5th place solution for Kaggle competition Favorita Grocery Sales Forecasting
Stars: ✭ 169 (+96.51%)
Mutual labels:  time-series, cnn
Kaggle Web Traffic Time Series Forecasting
Solution to Kaggle - Web Traffic Time Series Forecasting
Stars: ✭ 29 (-66.28%)
Mutual labels:  time-series, cnn
mtss-gan
MTSS-GAN: Multivariate Time Series Simulation with Generative Adversarial Networks (by @firmai)
Stars: ✭ 77 (-10.47%)
Mutual labels:  finance, time-series
Time Series Prediction
A collection of time series prediction methods: rnn, seq2seq, cnn, wavenet, transformer, unet, n-beats, gan, kalman-filter
Stars: ✭ 351 (+308.14%)
Mutual labels:  time-series, cnn
Deltapy
DeltaPy - Tabular Data Augmentation (by @firmai)
Stars: ✭ 344 (+300%)
Mutual labels:  time-series, finance
Fecon235
Notebooks for financial economics. Keywords: Jupyter notebook pandas Federal Reserve FRED Ferbus GDP CPI PCE inflation unemployment wage income debt Case-Shiller housing asset portfolio equities SPX bonds TIPS rates currency FX euro EUR USD JPY yen XAU gold Brent WTI oil Holt-Winters time-series forecasting statistics econometrics
Stars: ✭ 708 (+723.26%)
Mutual labels:  time-series, finance
Arch
ARCH models in Python
Stars: ✭ 660 (+667.44%)
Mutual labels:  time-series, finance
Indicators.jl
Financial market technical analysis & indicators in Julia
Stars: ✭ 130 (+51.16%)
Mutual labels:  time-series, finance
Msgarch
MSGARCH R Package
Stars: ✭ 51 (-40.7%)
Mutual labels:  time-series, finance
Pytorch Gan Timeseries
GANs for time series generation in pytorch
Stars: ✭ 109 (+26.74%)
Mutual labels:  time-series, finance
pybacen
This library was developed for economic analysis in the Brazilian scenario (Investments, micro and macroeconomic indicators)
Stars: ✭ 40 (-53.49%)
Mutual labels:  finance, time-series
Strategems.jl
Quantitative systematic trading strategy development and backtesting in Julia
Stars: ✭ 106 (+23.26%)
Mutual labels:  time-series, finance
Quantmod
Quantitative Financial Modelling Framework
Stars: ✭ 578 (+572.09%)
Mutual labels:  time-series, finance
Tensorflow Cnn Time Series
Feeding images of time series to Conv Nets! (Tensorflow + Keras)
Stars: ✭ 49 (-43.02%)
Mutual labels:  time-series, cnn
Fecon236
Tools for financial economics. Curated wrapper over Python ecosystem. Source code for fecon235 Jupyter notebooks.
Stars: ✭ 72 (-16.28%)
Mutual labels:  time-series, finance
Sdtw pytorch
Implementation of soft dynamic time warping in pytorch
Stars: ✭ 79 (-8.14%)
Mutual labels:  time-series
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1352.33%)
Mutual labels:  cnn

Can Machine Reads Like Analysts Do?

update:

Related paper: Trading via Image Classification (by J.P. Morgan)

Two Approaches

Approach 1

  • cnn4matrix.py

  • Apply convolution on data matrices directly.

Input: (5*n) matrices -> (Open,High,Low,Close,Volume)*(d1,d2,...,dn)

Output: classification result

Approach 2

  • cnn.py

  • Generate candlestick graphs first. sample

Input: candlestick graphs

Output: classification result

Current results

11 layers + residual block prediction

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].