https://github.com/levabd/prophet-finance-prediction

UAH/USD forecasting with prophet
https://github.com/levabd/prophet-finance-prediction

data-science forecasting jupyter-notebook machine-learning ml prophet python time-series

Last synced: 6 months ago
JSON representation

UAH/USD forecasting with prophet

• Host: GitHub
• URL: https://github.com/levabd/prophet-finance-prediction
• Owner: levabd
• License: mit
• Created: 2017-08-08T12:46:03.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2017-08-08T12:48:18.000Z (almost 9 years ago)
• Last Synced: 2024-03-26T06:54:51.066Z (over 2 years ago)
• Topics: data-science, forecasting, jupyter-notebook, machine-learning, ml, prophet, python, time-series
• Language: Jupyter Notebook
• Size: 455 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Predict fluctuations in currency quote using [Prophet](https://facebookincubator.github.io/prophet/)

![the forecast example](images/forecast_example.png)

## Overview

Let's try build model with help of [Prophet](https://facebookincubator.github.io/prophet/) to prеditi 

fluctuations in currency quotes. For current example I took currency pair UAH/USD for date range 2012-2017. 

Data was getting from https://www.investing.com/currencies/usd-uah-historical-data

The forecast looks quite realistic, the forecast components give some ideas about seasonality. 

The time series forecast can be used as a feature for another machine learning models.

[Prophet](https://facebookincubator.github.io/prophet/) works pretty well from the box. 

You can easily build a model for forecasting time series.

Also [Prophet](https://facebookincubator.github.io/prophet/docs/quick_start.html) several the hyperparameters, 

that can help you improve your model.

There are build in tools for visualization of the prediction. You can visulaizate the forecast and the forecast components.

The visualization of the forecast components can help make interesting conclusions about seasonality.

![the forecast components](images/yearly_seasonality.png)

## Dependencies

* Python 3.5

* [Prophet](https://facebookincubator.github.io/prophet/)

* [scikit-learn](http://scikit-learn.org/stable/)

* [plotly](https://plot.ly/python/offline/)