Social Media Intigration Cryptocurrancy Price Predition System - Bigdata Project

This Big Data project focuses on integrating social media data to predict cryptocurrency prices. By analyzing trends, sentiments, and discussions from platform Wikipedia Comments, the system generates real-time predictions on cryptocurrency price movements, leveraging machine learning and data analytics for more accurate forecasting.

API Reference

Import all Libraries for Sentiment Analysis

  import mwclient
  import time
  import transformers
  import mean
  import pandas

site = mwclient.Site('en.wikipedia.org')
page = site.pages['Bitcoin']

Import all Libraries for Sentiment Analysis and Crypto Prediction

  import yfinance as yf
  import os
  import pandas as pd
  import scikit-learn

  btc_ticker = yf.Ticker("BTC-USD")

Authors

• @Asindu Theekshana

Hi, I'm Asindu! 👋

🚀 About Me

I'm a Network Engineer...

🛠 Skills

HSRP, EIGRP, RIP, RIPv2, VPN, IP, HTML, CSS, PHP, JavaScript, MySQL, Boostrap, Wordpress...

🔗 Links

Other Common Github Profile Sections

👩‍💻 I'm currently work in YORK Graduate Campus...

🧠 I'm currently Studing for CISCO Exams...

💬 Ask me about Networking...

📫 [email protected]...

😄 He...

⚡️ Um Funny... HeHe..

Lessons Learned

The focus of this project is to enhance the prediction of cryptocurrency prices by utilizing sentiment analysis on social media and other advanced kinds of artificial intelligence. The project aims to develop a robust and comprehensive four-dimensional forecasting model by utilizing historical data, market coefficients, blockchain statistics, and sentiment analysis from platforms like Twitter. Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and XGBoost provide the potential to comprehensively capture the intricate patterns of the market owing to their intricate nature, hence ensuring a high level of accuracy and reliability. The research also examines novel methods of prediction and utilizes Big Data to evaluate substantial amounts of data and produce valuable insights and patterns. The end-users will derive advantages from the SEO reports, recommendations, and final analysis provided to the stakeholders in the dynamic and unpredictable bitcoin industry, enabling them to make informed decisions. The model demonstrates a high level of accuracy in reflecting the real-time fluctuations in the markets and provides insights into the efficacy of including sentiment analysis alongside or in combination with the quantitative measures for forecasting purposes.

Related

Here are some related projects

Bitcoin-Price-Prediction

BTC_Predictor

Bitcoin-Prediction

Support

For support, email [email protected]

Roadmap

• Install Python

• Install JupyterLab

• Install Power BI

Tech Stack

Language: Python

Software: JupyterLab, Power BI, Word, Excel