Scribd
Upload
17 views18 pages

Batch 10

The document outlines a major project focused on predicting cryptocurrency prices using machine learning techniques. It discusses the importance of handling sequential data, compares existing systems with proposed methods, and highlights the accuracy of various algorithms used. The conclusion emphasizes the need for caution in trading decisions and the potential for future research in this area.

Uploaded by

Godha Nemmarugommula
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
17 views18 pages

Batch 10

The document outlines a major project focused on predicting cryptocurrency prices using machine learning techniques. It discusses the importance of handling sequential data, compares existing systems with proposed methods, and highlights the accuracy of various algorithms used. The conclusion emphasizes the need for caution in trading decisions and the potential for future research in this area.

Uploaded by

Godha Nemmarugommula
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/ 18

Department of Computer Science and Business Systems

Major Project on
Cryptocurrency Price Prediction
using Machine Learning

Batch : 10
P. Gagan : 20P61A3214 Project Guide
K. Prasanna Laxmi : 20P61A3220 Mr. P. Hanumanth Rao
K.J.S Raghudatta : 20P61A3221 [Assistant professor | CSE]
Contents:
• Abstract
• Introduction
• Objective
• Requirements
• Existing System
• Proposed System
• Conclusion
• References
Abstract:

• Cryptocurrencies have emerged as important financial software systems. They rely on a secure distributed
ledger data structure; mining is integral to such systems. Mining adds records of past transactions to the
distributed ledger known as Blockchain, allowing users to reach secure, robust consensus for each
transaction.
• Cryptocurrency price prediction using machine learning has become a compelling and sought-after
application in the finance and data science domains.
• This research aims to explore the potential of machine learning algorithms in forecasting cryptocurrency
prices and providing insights into potential price trends.
Introduction:

• Given the time series nature of bitcoin pricing, extra consideration is given to processing sequential data
and minimizing data leakage during model training and assessment.
• Backtesting is used to recreate the model's performance on past data and estimate its prospective
profitability. While the research yields positive findings, it stresses the significance of taking a cautious
and educated approach to Bitcoin trading selections.
• Cryptocurrency markets are impacted by a variety of variables, including market sentiment, legislative
changes, technology breakthroughs, and macroeconomic events.
Objective:

• To develop a machine learning model for Crypto Currency Prediction, to potentially replace the
updatable supervised machine learning classification models by predicting leads to the shape of
best accuracy by comparing supervised algorithms.
• special attention is given to handling sequential data and avoiding data leakage during model
training and evaluation.
Requirements:

SOFTWARE REQUIREMENTS:
HARDWARE REQUIREMENTS
• Operating system : Windows 7 Ultimate or
above • Processor: 64-bit, four-core, 2.5 GHz minimum
per core
• Coding Language : Python
• RAM : 8GB
• Front-End : Python
• Hardisk : with a minimum memory of 40GB.
• IDE : VS Code, Google collab, Jupyter
notebook.
• Dataset : Kaggle(Cryptodata.csv)
Existing System:

• The issue will be successfully addressed by employing a Bayesian regression to its fullest extent.
• Long Short-Term Memory (LSTM) network and recurrent neural network (RNN) optimization. The
LST achieves the best RMSE of 8% and classification accuracy of 52%.In contrast to the deep learning
models, the well-known ARIMA model for time series forecasting is used.
• As anticipated, the non-linear deep learning techniques. beat the poor-performing ARIMA forecast.
Proposed System:

• Among many features of bitcoin, the most impressive one is decentralization that it can remove the
involvement of traditional financial sectors and monetary authorities effectively due to its blockchain network
features.
• Here the efficient usage of linear regression algorithm is used for predicting the prices of cryptocurrencies.
Accuracy of Algorithms involved:
Parameter Linear Regression Artificial Neural Long Short Term Recurrent Neural Decision Trees
Network Memory Network

Method Used Linear Regression Pattern Recognition Pattern Recognition Pattern Recognition Splitting data into
atleast 2 sets
Accuracy 97.59% 84.80% 92.30% 85.40% 95.88%
Complexity Simple Very High Moderate Very High Moderate
Speed Fastest Slow Moderate slow Fast
Advantages and • Fast training. • Can • Best forecast for • It is useful for • Generates
disadvantages • Low capability in approximate next day price sequence or time understandable
recognizing any continuous prediction. series data. rules.
longer term functions. • Requires more • Training data • Computationally
dependencies • Requires heavy memory to train. through RNN is Expensive.
computation a difficult task.
Architecture:
Use case Diagram:
Class Diagram:
Sequence Diagram:
Activity Diagram:
Conclusion:

• As a cautionary note, we emphasize that our machine-learning models should serve as complementary
tools rather than sole decision-makers for cryptocurrency trading and investment strategies
• Looking ahead, the evolving landscape of blockchain technology, advancements in machine learning, and
increasing data availability offer exciting opportunities for further research and improvements in
cryptocurrency price prediction.
References:

• International Journal of Advanced Research in Computer and Communication Engineering ISO


3297:2007,Impact Factor 8.102, Issue 4, April 2023 DOI: 10.17148/IJARCCE.2023.124140 ©
IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License
808 Cryptocurrency Price Prediction using Machine Learning.
• A Research On Bitcoin Price Prediction Using Machine Learning Algorithms, Lekkala Sreekanth
Reddy, Dr. P. Sriramya, 2020.
• Bitcoin Price Forecasting using LSTM and 10-Fold Cross validation, Sakshi Tandon, Shreya
Tripathi, Pragya Saraswat, Chetna Dabas, 2019.
• Deep Learning-Based Cryptocurrency Price Prediction Scheme With Inter-Dependent Relations,
October 15,2021 IEEE ACCESS
Links:

1. https://www.researchgate.net/publication/370516574_Cryptocurrency_Price_Prediction
_using_Machine_Learning
2. https://royalsocietypublishing.org/doi/10.1098/rsos.170623
3. https://ijcrt.org/papers/IJCRT2210098.pdf
4. https://thecleverprogrammer.com/2021/12/27/cryptocurrency-price-prediction-with-
machine-learning/
THANK YOU

You might also like