Dynamic Constant Product Market Maker Using Cryptocurrency Price Prediction Based on Deep Learning
- 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
-
- 파일 목록
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.