Description

General Description
Bitcoin, the first and most well-known cryptocurrency, has gained global attention due to its
decentralized nature, high volatility, and potential as a digital asset. Predicting its price is a
complex task influenced by market demand, investor sentiment, regulatory news, and
macroeconomic factors. Traditional statistical models often struggle with such nonlinear
and temporal dependencies. Long Short-Term Memory (LSTM) networks, a type of
recurrent neural network (RNN), are well-suited for time series forecasting due to their
ability to learn long-term patterns in sequential data. This project aims to leverage LSTM
models to predict future Bitcoin prices using historical price data and other relevant
indicators.

Project Scope
The purpose of this project is to develop an AI-based model that can accurately predict
future Crypto currencies (Bitcoin, Ethereum, Ripple) prices using historical data and
machine learning techniques. By applying LSTM neural networks, the project seeks to
capture temporal dependencies and complex patterns in cryptocurrency price movements.
The main objectives include collecting and preprocessing price data, designing and training
an LSTM model, evaluating its prediction accuracy, and analyzing the model’s performance
compared to traditional forecasting methods. Ultimately, the project aims to demonstrate
how deep learning can enhance financial forecasting in the volatile cryptocurrency market.
The students will deliver a GUI controlling and presenting the model output – historical and
real time.

Student Requirements
List expectations from students, such as:
- Teamwork
- Full attendance in weekly meetings
- High motivation
- Independent learning
- Personal responsibility

Development Tools
Tools and Technologies:
1. Programming Language:

Python – Primary language for data analysis, model building, and visualization.
2. Libraries and Frameworks:
NumPy, Pandas – For data manipulation and preprocessing.
Matplotlib, Seaborn – For data visualization and plotting model results.
TensorFlow / Keras or PyTorch – For building and training the LSTM neural network.
Scikit-learn – For scaling, evaluation metrics, and model comparison.
3. Data Sources:
Public APIs or datasets such as CoinBase, CoinGecko, CoinMarketCap, or Kaggle Bitcoin
historical price data.
4. Development Environment:
Jupyter Notebook / Google Colab / VSCode – For writing and testing code interactively.
5. Version Control:
Git &amp- GitHub – For collaboration and source code management.

Deliverables
List all required deliverables:
- Specification document
- YouTube video
- Poster
- Presentation
- GitHub link to the code
- GUI running the model

Additional Notes
• The project team may include up to 3 students.
• Please include your contact details at the end of the document for student inquiries:
- Full name: Dr. Ronen Almog
- Email address: drronenalmog@gmail.com
For any questions, you may also contact: Shirany.hit@gmail.com
Crypto currencies price prediction

Fintech and Blockchain

Description

Emphasis in project execution

The project is has cooperation with the industry and combines meeting deadlines while being creative and focused on the task
