https://github.com/navin772/gsoc_stock_prediction

Predict stock prices for short/long term using machine learning models and then deploy them on edge-core-cloud infrastructure using a data pipeline.
https://github.com/navin772/gsoc_stock_prediction

docker gsoc-2022 k8s machine-learning rancher

Last synced: 11 days ago
JSON representation

Predict stock prices for short/long term using machine learning models and then deploy them on edge-core-cloud infrastructure using a data pipeline.

• Host: GitHub
• URL: https://github.com/navin772/gsoc_stock_prediction
• Owner: navin772
• License: mit
• Created: 2022-06-23T09:38:46.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2023-09-02T07:12:00.000Z (over 1 year ago)
• Last Synced: 2023-09-03T08:43:31.001Z (over 1 year ago)
• Topics: docker, gsoc-2022, k8s, machine-learning, rancher
• Language: Jupyter Notebook
• Homepage: https://navin-stock.streamlitapp.com/
• Size: 8.77 MB
• Stars: 4
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# GSOC_Stock_prediction

![stock_image](https://www.umpindex.com/images/UMPI-Stock-Market-Projection-Software.png)

A ML model implementation on how to train a model on existing Index data and try to predict the future value of the Index.

This repository contains the following apps:

1. `index_prediction_app` - Made on flask and can be used to predict the future value of IXIC and NSE indices.

2. `streamlit_stock_app` - Made using Streamlit and uses LSTM and Prophet for stock/index predictions.

3. `fin_dashboard` - The latest iteration of the app, contains many useful features for comparisons, predictions and chart visualization.

All 3 apps are deployable as containers using the provided dockerfile in their respective directory and can also orchestrated using kustomize on any k8s cluster. The directory also contains the YAML files for the deployment.

For deployment instructions refer to the documentation inside each app directory.

Visit my Medium account to read detailed blogs for the work done here - [Medium-Navin Chandra](https://medium.com/@navinchandra772)

To see a video demonstration of this project refer this [Video](https://drive.google.com/file/d/1oBYy61PSsp0q2GSQtnOzakinzLTVCv2y/view?usp=sharing) or the [official presentation](https://www.youtube.com/watch?v=D2mFfApyS_Q&t=1354s) uploaded to openSUSE youtube channel.

Read the getting started guide on the [SUSE documentation](https://documentation.suse.com/trd/kubernetes/single-html/gs_rancher_edge-analytics_finance_stocks/) page.

 ## Mentors

 This project was done during **Google Summer of Code 2022** and was mentored by [Bryan Gartner](https://github.com/bwgartner), [Brian Fromme](https://github.com/mrjazzcat), [Ann Davis](https://github.com/andavissuse) and [Terry Smith](https://github.com/tlssuse).

 

 Organization - [openSUSE](https://www.opensuse.org/)

 GSoC Project - [Analytics Edge Ecosystem Workloads](https://summerofcode.withgoogle.com/programs/2022/projects/wvb53CUA)