OAK

Dynamic Constant Product Market Maker Using Cryptocurrency Price Prediction Based on Deep Learning

Metadata Downloads
Author(s)
Ha-young Park
Type
Thesis
Degree
Master
Department
대학원 전기전자컴퓨터공학부
Advisor
Lee, Heung-No
Abstract
These days the Decentralized Finance(DeFi) market has grown. In particular, the Decentralized Exchange(DEX) is the most popular and large DeFi application. A great number of DEX use Automated Market Maker(AMM) which is a mathematical algorithm to decide the price of the assets. However, AMM has drawbacks called slippage and impermanent loss. In this paper, we briefly review the related concepts and dynamic curves introduced by Bhaskar et al. We suggest a dynamic constant product market maker using cryptocurrency price prediction based on deep learning. Using cryptocurrency price prediction based on deep learning, our system aims to give lower latency and higher accurate price than using decentralized oracle data feed. Changing the curve following the predicted price, the system can mitigate impermanent loss and give more profit to liquidity providers.
URI
https://scholar.gist.ac.kr/handle/local/19203
Fulltext
http://gist.dcollection.net/common/orgView/200000883511
공개 및 라이선스
  • 공개 구분공개
파일 목록
  • 관련 파일이 존재하지 않습니다.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.