GNN-Based Crypto Recommender for Maximized ROI using GNN based models(Ex: LightGCN and GraphSage)
Budget: ₹12,500 – ₹37,500 INR
I'm looking for a skilled data scientist with experience in building recommender systems, specifically using Graph Neural Networks (GNN) models such as LightGCN and GraphSage. The project involves creating a personalized recommender engine for cryptocurrencies.
Key Requirements:
- Utilizing diverse data sources: The recommender engine should leverage transaction data, social media trends, and market prices.
- Primary objective: The main goal of this engine is to maximize investment returns.
- Personalization: The system should tailor recommendations based on the user's past transactions and their preferred cryptocurrencies.
- Integrate real-time data feeds from various cryptocurrency exchanges and social media platforms.
Ideal Candidates:
- Proven experience with GNN models, particularly LightGCN and GraphSage.
- Strong understanding of cryptocurrency market dynamics.
- Ability to interpret and utilize multi-source data for building effective recommender systems.
The GNN-based recommender should be deployed as a web-based platform. The recommender should use general user preferences. The development should primarily use Python. The recommender engine should achieve high accuracy in its recommendations. The platform should allow users to provide feedback and adjust recommendation settings. Users should be able to rate the recommendations to improve the accuracy of future suggestions. A minimalistic user interface design is required. The recommender engine should integrate real-time data feeds via APIs from various cryptocurrency exchanges and social media platforms.
Key Requirements:
- Utilizing diverse data sources: The recommender engine should leverage transaction data, social media trends, and market prices.
- Primary objective: The main goal of this engine is to maximize investment returns.
- Personalization: The system should tailor recommendations based on the user's past transactions and their preferred cryptocurrencies.
- Integrate real-time data feeds from various cryptocurrency exchanges and social media platforms.
Ideal Candidates:
- Proven experience with GNN models, particularly LightGCN and GraphSage.
- Strong understanding of cryptocurrency market dynamics.
- Ability to interpret and utilize multi-source data for building effective recommender systems.
The GNN-based recommender should be deployed as a web-based platform. The recommender should use general user preferences. The development should primarily use Python. The recommender engine should achieve high accuracy in its recommendations. The platform should allow users to provide feedback and adjust recommendation settings. Users should be able to rate the recommendations to improve the accuracy of future suggestions. A minimalistic user interface design is required. The recommender engine should integrate real-time data feeds via APIs from various cryptocurrency exchanges and social media platforms.