Heroku_Graph_ML

Deployed Using Heroku at https://dspyt.herokuapp.com/

We are accessing Uniswap V3 GraphQL at https://thegraph.com/hosted-service/subgraph/uniswap/uniswap-v3?selected=playground to obtain historical data for the chosen token. The Default token is Uniswap.

Next we model the time-series data to predict token price for the N number of timestamps. Default is 15 periods.

Model

We have Used Arima(1,1,0) model since it has maths foundation and differences the data to make it stationary.

In particular properties of AR(1) are as following:

We are also using the app to create a larger app for the Uniswap bounty. The app output

Further References

DSPYT: Time series data – An easy introduction

DSPYT: Simple Return, Log Return and Volatility easy intro

DSPYT: Advanced Realized Volatility and Quarticity

DSPYT: Machine Learning simple Sklearn Ensemble