Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cryptocurrency Price Forecasting Using XGBoost Regressor and Technical Indicators

Abdelatif Hafid, Maad Ebrahim, Ali Alfatemi, Mohamed Rahouti, Diogo Oliveira

TL;DR

This paper tackles Bitcoin price forecasting in a highly volatile cryptocurrency market. It proposes an XGBoost regressor that ingests historical price/volume data and a suite of technical indicators, including EMA, MACD, RSI, MOM, and %K. Through grid-search tuned regularization and a 15-minute Binance-based dataset from 2021-02-01 to 2022-02-01, it achieves RMSE $=59.9504$, MAE $=46.2229$, and $R^2 \approx 0.9999$ on the test set. The results suggest a robust, scalable approach for traders in dynamic markets, with practical implications for crypto price forecasting.

Abstract

The rapid growth of the stock market has attracted many investors due to its potential for significant profits. However, predicting stock prices accurately is difficult because financial markets are complex and constantly changing. This is especially true for the cryptocurrency market, which is known for its extreme volatility, making it challenging for traders and investors to make wise and profitable decisions. This study introduces a machine learning approach to predict cryptocurrency prices. Specifically, we make use of important technical indicators such as Exponential Moving Average (EMA) and Moving Average Convergence Divergence (MACD) to train and feed the XGBoost regressor model. We demonstrate our approach through an analysis focusing on the closing prices of Bitcoin cryptocurrency. We evaluate the model's performance through various simulations, showing promising results that suggest its usefulness in aiding/guiding cryptocurrency traders and investors in dynamic market conditions.

Cryptocurrency Price Forecasting Using XGBoost Regressor and Technical Indicators

TL;DR

This paper tackles Bitcoin price forecasting in a highly volatile cryptocurrency market. It proposes an XGBoost regressor that ingests historical price/volume data and a suite of technical indicators, including EMA, MACD, RSI, MOM, and %K. Through grid-search tuned regularization and a 15-minute Binance-based dataset from 2021-02-01 to 2022-02-01, it achieves RMSE , MAE , and on the test set. The results suggest a robust, scalable approach for traders in dynamic markets, with practical implications for crypto price forecasting.

Abstract

The rapid growth of the stock market has attracted many investors due to its potential for significant profits. However, predicting stock prices accurately is difficult because financial markets are complex and constantly changing. This is especially true for the cryptocurrency market, which is known for its extreme volatility, making it challenging for traders and investors to make wise and profitable decisions. This study introduces a machine learning approach to predict cryptocurrency prices. Specifically, we make use of important technical indicators such as Exponential Moving Average (EMA) and Moving Average Convergence Divergence (MACD) to train and feed the XGBoost regressor model. We demonstrate our approach through an analysis focusing on the closing prices of Bitcoin cryptocurrency. We evaluate the model's performance through various simulations, showing promising results that suggest its usefulness in aiding/guiding cryptocurrency traders and investors in dynamic market conditions.
Paper Structure (11 sections, 10 equations, 3 figures, 4 tables)

This paper contains 11 sections, 10 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data
  4. Data Collection and Preprocessing
  5. Feature Engineering
  6. Historical Data
  7. Technical Indicators
  8. Methodology
  9. Results and Analysis
  10. State-of-the-Art Comparison
  11. Conclusion

Figures (3)

  • Figure 1: Bitcoin close price over time.
  • Figure 2: Scatter plot showing the residuals against the predicted values.
  • Figure 3: Scatter plot of actual vs. predicted values.