Home A - Z
Page Index

Sentify

Turning News-Based-Sentiment into Crypto Certainty..

Team: Teams/Team Apex

Project Status: Planning

Project Overview


The Problem

Signal-to-Noise Problem

  • The crypto market thrives on constant online chatter — from influencers, news sources, and discussion forums — but manually analyzing this flood of information is nearly impossible.
  • Traders struggle to distinguish authentic market-moving insights from distractions like scams, bots, and irrelevant commentary.

Lack of Quantified Sentiment

  • News-Based-Sentiment is one of the primary drivers of crypto volatility, yet most traders lack a reliable, data-driven way to measure it.
  • There is no objective, probabilistic tool that links market conversation directly to actionable price predictions, leaving traders to rely on intuition instead of insight.


Our AI Solution

What It Does ? 🎯

  • Delivers real-time alerts on global crypto-related news — complete with a probability score showing whether the event is likely to move the market positively or negatively.

  • Replaces emotional, reactionary trading with clear, data-driven insights so you can make confident Long/Short decisions.

How It Works ? ⚙️

  • Ingestion: Continuously scans trusted global news sources, forums, and updates relevant to crypto.

  • AI: Our specialized NLP model interprets the context, detects sentiment, and evaluates the credibility of the information.

  • Prediction: A probabilistic model correlates sentiment intensity and relevance with potential market impact.

  • Output: Users receive instant notifications with a predicted percentage — telling you if the news is likely bullish or bearish — so you never miss a market-moving event.


Technology Stack

  • AI/ML Models: (Gemini API)
  • Frameworks & Libraries: (PyTorch, LangChain)
  • Backend: (Python, Node.js)
  • Frontend: (Flutter)
  • Databases: (PostgreSQL with pgvector, Redis, Firebase)
  • Deployment & Tools: (Docker, Git, AWS)
  • APIs Used: (coingecko.com)


Project Architecture

Sentify is an AI-powered mobile application designed to provide cryptocurrency traders and enthusiasts with timely, actionable intelligence. The system ingests and analyzes a high volume of news, identifies high-impact events through sentiment analysis, and delivers personalized alerts to users based on their interests and sensitivity preferences. The architecture is designed around modern, decoupled modules to ensure scalability, resilience, and maintainability. It consists of three primary, independent services that communicate asynchronously through a central database and a task queue.

Module 1: Data Ingestion & Processing Pipeline

Objective: Continuously fetch, clean, and analyze crypto news.

Technology: Python, Scrapy, Sentence-Transformers, LangChain, Gemini API.

Process Flow:

  • Fetch new articles from trusted sources.

  • Preprocess text, remove duplicates, and normalize data.

  • Run sentiment & credibility analysis via Gemini API.

  • Store processed articles in PostgreSQL with vector embeddings.

Module 2: The Alerting Engine

Objective: TDeliver real-time, personalized alerts for high-impact news.

Technology: Python, Redis, PostgreSQL.

Process Flow:

  • Detect new sentiment-analyzed articles.

  • Match articles to users based on watchlist and alert thresholds.

  • Build payload and send notifications via FCM.

  • Track delivery and engagement for analytics.

Module 3: Backend API

Objective:
To serve as the secure and efficient interface between the Sentify mobile app and the backend ecosystem.

Technology: NodeJS, PostgreSQL.

Key Responsibilities:

  • Manage user accounts, authentication, and profiles.

  • Provide CRUD for watchlists and notification settings.

  • Serve live market data, news feeds, and historical sentiment.

  • Ensure security, caching, and performance optimization.

Later, all three users open the Sentify App. The Backend API serves them the dashboard, where they can all see the negative news item in their feed.

Architecture Diagram:

Sequence Diagram:

Flow chart Diagram:

HLD

Sentify

Design

Figma

Challenges & Learnings

Building Sentify involved solving complex technical problems across AI, backend, frontend, and deployment layers. The hardest challenges and the biggest learnings include:

1. Understanding AI Models & Prompt Engineering

We had to learn how AI models interpret text, score sentiment, and classify news with accuracy. Creating prompts that consistently produce reliable results was challenging, but it helped us master effective prompt engineering and understand how small changes in prompts can dramatically affect outputs.

2. Working With Vector Embeddings

This was our first time using vector databases (pgvector) and learning how embeddings store semantic meaning. Understanding similarity search and how to structure news embeddings for fast retrieval was a major learning milestone.

3. Python Ecosystem & NLP Processing

We learned Python more deeply — from building ingestion pipelines to integrating NLP models, handling async tasks, and optimizing data processing. This included working with libraries like Sentence-Transformers, LangChain, and the Gemini API.

4. Backend & Infrastructure Challenges

We faced challenges in:

  • Setting up servers for both Python and Node.js

  • Managing API scaling and efficient database querying

  • Learning Redis Stack for caching, real-time alerting, and queueing

  • Implementing Sequelize ORM with PostgreSQL

These tasks strengthened our backend architecture and deployment skills.

5. Frontend Challenges (Flutter)

The most difficult part on the frontend was:

  • Integrating real-time graphs with news sentiment

  • Syncing graph data with live market trends

  • Managing API delays, inconsistent data formats, and UI refresh issues

This helped us better understand state management and dynamic data visualization.

6. Project & Time Management

Coordinating three different modules (AI, alerting engine, backend) within a short time was challenging. We learned:

  • How to divide responsibilities smartly

  • Use AI tools to speed up development

  • Manage scope, deadlines, and deliverables

Future Roadmap

If this project continues, here are the strategic next steps:

Short-Term Goals (0–2 months)

  • Increase sentiment prediction accuracy.

  • Improve noise filtering and source credibility scoring

  • Enhance Flutter UI for smoother live chart rendering

  • Optimize ingestion pipeline for faster turnaround

  • Begin analysis of additional news resources, sources, and feeds to expand coverage

Medium-Term Goals (2–6 months)

  • Launch the Sentify Mobile App (Flutter) publicly

  • Add multi-source comparative analysis (impact ranking from different news outlets)

  • Introduce custom user alert rules (coin-specific, FUD alerts, volume spikes, etc.)

  • Build a web-based analytics dashboard for historical sentiment

  • Expand ingestion to niche crypto sources (DeFi blogs, GitHub updates, developer notes)

Long-Term Goals (6+ months)

  • Build an Admin Web Application for controlling ingestion pipeline, users, source management, and system monitoring

  • Introduce automated trading signal suggestions based on long-term sentiment patterns

  • Add multilingual news support for global coverage

  • Deploy an enterprise API for institutional users and trading firms

Repository & Live Demo

Screenshots / Demo Video

Categories: #project #ai-hackathon-[year] #category-[your-topic]