In this repository we present a few examples for trading analytics that leverage
the nonlinear optimisation platform NOA
and its experimental kotlin-jvm
frontend
within the KMath library.
To use kmath-noa, you will need first to build & publish the module locally.
For data storage, you have to install MongoDB. You can edit the configurations in the conf.yaml file.
In this study, we explore the impact of High Frequency Trading on execution costs and liquidity for several Cryptocurrency exchanges.
You will find the data collection utilities within crypto-hft-data. To run the app you need to simply execute:
./gradlew -Dorg.gradle.java.home=/path/to/local/jdk -q :crypto-hft-data:run --args=/path/to/conf.yaml
You can configure it in conf.yaml to get the LOB data feed from the following exchanges and liquidity aggregators:
for any of the traded instruments available on the platforms.
Once you've collected a bit of data you can run the analysis with the models we provide in crypto-hft-client and crypto-hft-analytics.
The module crypto-hft-visual provides the visualisation apps.
We are very grateful to contributions from:
We kindly acknowledge support from Finery Markets, GrinisRIT ltd. and JetBrains Research.
(c) 2021 GrinisRIT ltd. and contributors