Predicting financial markets has always been a great challenge. In the recent years, the rise of notoriety of the blockchain technology has made cryptocurrencies more popular and considered by many as financial assets. However, the crypto market has been unregulated and this also contributes to its volatile nature hence making its predictiveness even more challenging. The scope of this work is to evaluate if machine learning predictive methods could be used in making predictions in the crypto market. The ML algorithms used are Random Forest, XG Boost and Light GBM. Further analysis was done comparing their performances with some known technical indicator trading strategies like the Exponential moving average (EMA), Relative Strength Index(RSI) etc.

Predicting Crypto Assets using Machine Learning & Technical Analysis Techniques

Simeon, Osemwengie Cyril
2022/2023

Abstract

Predicting financial markets has always been a great challenge. In the recent years, the rise of notoriety of the blockchain technology has made cryptocurrencies more popular and considered by many as financial assets. However, the crypto market has been unregulated and this also contributes to its volatile nature hence making its predictiveness even more challenging. The scope of this work is to evaluate if machine learning predictive methods could be used in making predictions in the crypto market. The ML algorithms used are Random Forest, XG Boost and Light GBM. Further analysis was done comparing their performances with some known technical indicator trading strategies like the Exponential moving average (EMA), Relative Strength Index(RSI) etc.
2022-10-20
File in questo prodotto:
File Dimensione Formato  
868355-1269089.pdf

non disponibili

Tipologia: Altro materiale allegato
Dimensione 3.42 MB
Formato Adobe PDF
3.42 MB Adobe PDF

I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14247/8248