Scribd
Upload
9 views1 page

ABSTRACT PG Mini

This project investigates the use of Long Short-Term Memory (LSTM) networks for predicting Bitcoin prices, addressing challenges posed by the cryptocurrency's volatility. The methodology includes data preprocessing, hyperparameter tuning, and evaluation through metrics like RMSE and MAE. While the results indicate the effectiveness of LSTM models, the study suggests exploring advanced and hybrid approaches for enhanced prediction accuracy.

Uploaded by

14suriya02
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
9 views1 page

ABSTRACT PG Mini

This project investigates the use of Long Short-Term Memory (LSTM) networks for predicting Bitcoin prices, addressing challenges posed by the cryptocurrency's volatility. The methodology includes data preprocessing, hyperparameter tuning, and evaluation through metrics like RMSE and MAE. While the results indicate the effectiveness of LSTM models, the study suggests exploring advanced and hybrid approaches for enhanced prediction accuracy.

Uploaded by

14suriya02
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

ABSTRACT

This project focuses on predicting Bitcoin prices using Long Short-Term Memory
(LSTM) networks, a type of Recurrent Neural Network (RNN) known for effectively capturing
long-term dependencies in sequential data. Given Bitcoin's volatility and non-linear price
patterns, traditional models often struggle to provide accurate forecasts, making LSTM a suitable
alternative for time-series prediction. The dataset comprises historical Bitcoin prices, with
preprocessing steps like normalization and data splitting applied to improve model performance.
Techniques such as hyper parameter tuning and dropout layers are used to prevent overfitting and
enhance accuracy. The model’s predictions are evaluated using metrics like Root Mean Squared
Error (RMSE) and Mean Absolute Error (MAE) to ensure reliability. This project demonstrates
how machine learning can support informed decision-making in crypto currency markets by
providing data-driven insights. While the results show the potential of LSTM models, they also
highlight limitations, suggesting further exploration of advanced and hybrid approaches for
improved accuracy.

You might also like