# crypto price prediction using lstm+xgboost

arXiv: https://arxiv.org/abs/2506.22055 · HTML: https://mlsanity.com/paper/2506.22055/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 52 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [LSTM Based Sentiment Analysis for Cryptocurrency Prediction](https://mlsanity.com/paper/2103.14804/) (2021)
- [Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction](https://mlsanity.com/paper/2204.02623/) (2022)
- [A Novel Hybrid Approach Using an Attention-Based Transformer + GRU Model for Predicting Cryptocurrency Prices](https://mlsanity.com/paper/2504.17079/) (2025)
- [Stock Price Prediction Using a Hybrid LSTM-GNN Model: Integrating Time-Series and Graph-Based Analysis](https://mlsanity.com/paper/2502.15813/) (2025)

## Abstract (arXiv)

The volatility and complex dynamics of cryptocurrency markets present unique challenges for accurate price forecasting. This research proposes a hybrid deep learning and machine learning model that integrates Long Short-Term Memory (LSTM) networks and Extreme Gradient Boosting (XGBoost) for cryptocurrency price prediction. The LSTM component captures temporal dependencies in historical price data, while XGBoost enhances prediction by modeling nonlinear relationships with auxiliary features such as sentiment scores and macroeconomic indicators. The model is evaluated on historical datasets of Bitcoin, Ethereum, Dogecoin, and Litecoin, incorporating both global and localized exchange data. Comparative analysis using Mean Absolute Percentage Error (MAPE) and Min-Max Normalized Root Mean Square Error (MinMax RMSE) demonstrates that the LSTM+XGBoost hybrid consistently outperforms standalone models and traditional forecasting methods. This study underscores the potential of hybrid architectures in financial forecasting and provides insights into model adaptability across different cryptocurrencies and market contexts.