Blame
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 1 | > <center><h1> <b>Sentify <br> <h4>Turning News-Based-Sentiment into Crypto Certainty..</h4> </b></h1></center> |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 2 | |
| eeda46 | Nikhil | 2025-09-25 07:27:28 | 3 | <!-- **Tagline:** **Turning News-Based-Sentiment into Crypto Certainty..** --> |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 4 | |
| a5b258 | Sakshi Mahajan | 2025-09-24 10:55:55 | 5 | **Team:** [[Teams/Team Apex]] |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 6 | |
| 8ddc47 | Sakshi Mahajan | 2025-11-28 11:14:40 | 7 | **Project Status:** Deployment Phase |
| bbb2f3 | Sakshi Mahajan | 2025-10-09 13:36:36 | 8 | |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 9 | |
| 10 | ||||
| 0f2c3a | Sakshi Mahajan | 2025-10-09 09:06:24 | 11 | > ### Project Overview |
| d41716 | Sakshi Mahajan | 2025-09-25 06:16:31 | 12 | ::: warning |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 13 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 14 | Crypto markets move at lightning speed, driven by global news, community sentiment, and collective emotion — not just price charts. Most traders struggle to keep up, relying on gut feelings or reacting too late. |
| 15 | ||||
| 16 | Sentify is your AI-powered market analyst, cutting through the noise of endless news and chatter to deliver only what matters. Our system continuously scans global crypto news and events, analyzes their credibility and sentiment, and transforms them into clear, probability-based insights. |
|||
| 17 | ||||
| 308b60 | Sakshi Mahajan | 2025-09-25 06:42:53 | 18 | The result: instant alerts with a predicted score showing whether an event is likely to push the market up or down — empowering you to trade with data, not emotion. |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 19 | |
| 20 | Our goal is simple: stop guessing, start trading on quantified market probability. |
|||
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 21 | |
| 362cce | Sakshi Mahajan | 2025-09-24 11:53:12 | 22 | ::: |
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 23 | |
| 24 | <br></br> |
|||
| 0f2c3a | Sakshi Mahajan | 2025-10-09 09:06:24 | 25 | > ### The Problem |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 26 | |
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 27 | |
| c856a7 | Sakshi Mahajan | 2025-10-09 09:07:20 | 28 | **Signal-to-Noise Problem** |
| fbdff2 | Yash Hanj | 2025-10-09 06:44:33 | 29 | |
| 0f2c3a | Sakshi Mahajan | 2025-10-09 09:06:24 | 30 | - 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. |
| 31 | - **Traders struggle to distinguish authentic market-moving insights from distractions** like scams, bots, and irrelevant commentary. |
|||
| fbdff2 | Yash Hanj | 2025-10-09 06:44:33 | 32 | |
| 33 | ||||
| c856a7 | Sakshi Mahajan | 2025-10-09 09:07:20 | 34 | **Lack of Quantified Sentiment** |
| fbdff2 | Yash Hanj | 2025-10-09 06:44:33 | 35 | |
| 0f2c3a | Sakshi Mahajan | 2025-10-09 09:06:24 | 36 | - News-Based-Sentiment is one of the primary drivers of crypto volatility, yet most traders lack a reliable, data-driven way to measure it. |
| 37 | - There is **no objective, probabilistic tool** that links market conversation directly to actionable price predictions, leaving traders to rely on **intuition instead of insight**. |
|||
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 38 | |
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 39 | |
| 40 | <br></br> |
|||
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 41 | > ## Our AI Solution |
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 42 | |
| 43 | ||||
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 44 | **What It Does ? 🎯** |
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 45 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 46 | - 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. |
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 47 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 48 | - Replaces emotional, reactionary trading with clear, data-driven insights so you can make confident Long/Short decisions. |
| ab95eb | Sakshi Mahajan | 2025-09-24 11:07:33 | 49 | |
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 50 | **How It Works ? ⚙️** |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 51 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 52 | - **Ingestion:** Continuously scans trusted global news sources, forums, and updates relevant to crypto. |
| c2e20b | Sakshi Mahajan | 2025-09-25 05:55:12 | 53 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 54 | - **AI:** Our specialized NLP model interprets the context, detects sentiment, and evaluates the credibility of the information. |
| c2e20b | Sakshi Mahajan | 2025-09-25 05:55:12 | 55 | |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 56 | - **Prediction:** A probabilistic model correlates sentiment intensity and relevance with potential market impact. |
| c2e20b | Sakshi Mahajan | 2025-09-25 05:55:12 | 57 | |
| 308b60 | Sakshi Mahajan | 2025-09-25 06:42:53 | 58 | - **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. |
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 59 | |
| 60 | <br></br> |
|||
| eeda46 | Nikhil | 2025-09-25 07:27:28 | 61 | > ## Technology Stack |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 62 | |
| fd1f7c | Nikhil | 2025-09-25 06:39:30 | 63 | * **AI/ML Models:** (Gemini API) |
| 49d809 | Sakshi Mahajan | 2025-11-28 11:12:04 | 64 | * **Frameworks & Libraries:** (PyTorch, LangChain) |
| 65 | * **Backend:** (Python, Node.js) |
|||
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 66 | * **Frontend:** (Flutter) |
| fd1f7c | Nikhil | 2025-09-25 06:39:30 | 67 | * **Databases:** (PostgreSQL with pgvector, Redis, Firebase) |
| 7a0364 | Sakshi Mahajan | 2025-09-25 06:14:19 | 68 | * **Deployment & Tools:** (Docker, Git, AWS) |
| 49d809 | Sakshi Mahajan | 2025-11-28 11:12:04 | 69 | * **APIs Used:** (coingecko.com) |
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 70 | |
| 28e939 | Sakshi Mahajan | 2025-09-25 09:12:47 | 71 | <br></br> |
| 4b74a3 | Sakshi Mahajan | 2025-09-25 09:07:49 | 72 | |
| eeda46 | Nikhil | 2025-09-25 07:27:28 | 73 | > ## Project Architecture |
| c921db | Sakshi Mahajan | 2025-10-08 09:42:09 | 74 | |
| 804f87 | Sakshi Mahajan | 2025-10-09 07:27:07 | 75 | 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. |
| f2d4c0 | Sakshi Mahajan | 2025-10-09 07:17:32 | 76 | 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.<br> |
| 77 | ||||
| c921db | Sakshi Mahajan | 2025-10-08 09:42:09 | 78 | |
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 79 | **Module 1: Data Ingestion & Processing Pipeline**<br> |
| 80 | ||||
| 754f6b | Sakshi Mahajan | 2025-10-09 07:16:20 | 81 | **Objective:** Continuously fetch, clean, and analyze crypto news.<br> |
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 82 | |
| 83 | **Technology:** Python, Scrapy, Sentence-Transformers, LangChain, Gemini API.<br> |
|||
| 84 | ||||
| 85 | **Process Flow:** |
|||
| 754f6b | Sakshi Mahajan | 2025-10-09 07:16:20 | 86 | * Fetch new articles from trusted sources. |
| 87 | ||||
| 88 | * Preprocess text, remove duplicates, and normalize data. |
|||
| 89 | ||||
| 90 | * Run sentiment & credibility analysis via Gemini API. |
|||
| 91 | ||||
| 92 | * Store processed articles in PostgreSQL with vector embeddings. |
|||
| c921db | Sakshi Mahajan | 2025-10-08 09:42:09 | 93 | |
| 94 | **Module 2: The Alerting Engine**<br> |
|||
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 95 | |
| 754f6b | Sakshi Mahajan | 2025-10-09 07:16:20 | 96 | **Objective:** TDeliver real-time, personalized alerts for high-impact news.<br> |
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 97 | |
| 98 | **Technology:** Python, Redis, PostgreSQL. |
|||
| 99 | ||||
| 100 | **Process Flow:** |
|||
| 101 | ||||
| 754f6b | Sakshi Mahajan | 2025-10-09 07:16:20 | 102 | * Detect new sentiment-analyzed articles. |
| 103 | ||||
| 104 | * Match articles to users based on watchlist and alert thresholds. |
|||
| 105 | ||||
| 106 | * Build payload and send notifications via FCM. |
|||
| 107 | ||||
| 108 | * Track delivery and engagement for analytics. |
|||
| c921db | Sakshi Mahajan | 2025-10-08 09:42:09 | 109 | |
| 110 | **Module 3: Backend API**<br> |
|||
| 3d8d22 | Sakshi Mahajan | 2025-10-09 07:09:18 | 111 | |
| 112 | **Objective:**<br> To serve as the secure and efficient interface between the Sentify mobile app and the backend ecosystem.<br> |
|||
| 113 | ||||
| 114 | **Technology:** NodeJS, PostgreSQL.<br> |
|||
| 115 | ||||
| 116 | **Key Responsibilities:** |
|||
| 754f6b | Sakshi Mahajan | 2025-10-09 07:16:20 | 117 | * Manage user accounts, authentication, and profiles. |
| 118 | ||||
| 119 | * Provide CRUD for watchlists and notification settings. |
|||
| 120 | ||||
| 121 | * Serve live market data, news feeds, and historical sentiment. |
|||
| 122 | ||||
| 123 | * Ensure security, caching, and performance optimization. |
|||
| c921db | Sakshi Mahajan | 2025-10-08 09:42:09 | 124 | 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. |
| 212436 | Sakshi Mahajan | 2025-10-09 07:19:20 | 125 | |
| 3dc686 | Sakshi Mahajan | 2025-10-09 09:30:28 | 126 | |
| 127 | > ## Architecture Diagram: |
|||
| 128 | > |
|||
| 570ce1 | Sakshi Mahajan | 2025-10-08 09:43:51 | 129 |  |
| 130 | ||||
| 175351 | Nikhil | 2025-10-09 09:01:26 | 131 | |
| 132 | ||||
| 3dc686 | Sakshi Mahajan | 2025-10-09 09:30:28 | 133 | > ## Sequence Diagram: |
| 175351 | Nikhil | 2025-10-09 09:01:26 | 134 |  |
| 135 | ||||
| 136 | ||||
| 3dc686 | Sakshi Mahajan | 2025-10-09 09:30:28 | 137 | > ## Flow chart Diagram: |
| 1aca1e | Nikhil | 2025-10-09 09:02:25 | 138 | |
| 212a8c | Nikhil | 2025-10-09 09:01:58 | 139 |  |
| 175351 | Nikhil | 2025-10-09 09:01:26 | 140 | |
| 141 | ||||
| 3edfe3 | Nikhil | 2025-10-09 08:52:39 | 142 | > ## HLD |
| 143 | [Sentify](./Sentify.pdf) |
|||
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 144 | |
| 14b233 | Nikhil | 2025-10-09 08:49:00 | 145 | > ## Design |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 146 | |
| 0bd118 | Sakshi Mahajan | 2025-12-08 06:43:06 | 147 | [Figma](https://www.figma.com/proto/aWlzR7xBsneLVtamlXrZRx/Untitled?node-id=2108-407&p=f&t=SaB5IgxxBitC0x1f-1&scaling=scale-down&content-scaling=fixed&page-id=2013%3A1508) |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 148 | |
| eeda46 | Nikhil | 2025-09-25 07:27:28 | 149 | > ## Challenges & Learnings |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 150 | |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 151 | Building Sentify involved solving complex technical problems across AI, backend, frontend, and deployment layers. The hardest challenges and the biggest learnings include: |
| 152 | ||||
| 153 | #### 1. Understanding AI Models & Prompt Engineering |
|||
| 154 | ||||
| 155 | 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. |
|||
| 156 | ||||
| 157 | #### 2. Working With Vector Embeddings |
|||
| 158 | ||||
| 49d809 | Sakshi Mahajan | 2025-11-28 11:12:04 | 159 | 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. |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 160 | |
| 161 | #### 3. Python Ecosystem & NLP Processing |
|||
| 162 | ||||
| 49d809 | Sakshi Mahajan | 2025-11-28 11:12:04 | 163 | 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. |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 164 | |
| 165 | #### 4. Backend & Infrastructure Challenges |
|||
| 166 | ||||
| 167 | We faced challenges in: |
|||
| 168 | ||||
| 49d809 | Sakshi Mahajan | 2025-11-28 11:12:04 | 169 | - Setting up servers for both Python and Node.js |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 170 | |
| 171 | - Managing API scaling and efficient database querying |
|||
| 172 | ||||
| 173 | - Learning Redis Stack for caching, real-time alerting, and queueing |
|||
| 174 | ||||
| 175 | - Implementing Sequelize ORM with PostgreSQL |
|||
| 176 | These tasks strengthened our backend architecture and deployment skills. |
|||
| 177 | ||||
| 178 | #### 5. Frontend Challenges (Flutter) |
|||
| 179 | ||||
| 180 | The most difficult part on the frontend was: |
|||
| 181 | ||||
| 182 | - Integrating real-time graphs with news sentiment |
|||
| 183 | ||||
| 184 | - Syncing graph data with live market trends |
|||
| 185 | ||||
| 186 | - Managing API delays, inconsistent data formats, and UI refresh issues |
|||
| 187 | This helped us better understand state management and dynamic data visualization. |
|||
| 188 | ||||
| 189 | #### 6. Project & Time Management |
|||
| 190 | ||||
| 191 | Coordinating three different modules (AI, alerting engine, backend) within a short time was challenging. |
|||
| 192 | We learned: |
|||
| 193 | ||||
| 194 | - How to divide responsibilities smartly |
|||
| 195 | ||||
| 196 | - Use AI tools to speed up development |
|||
| 197 | ||||
| 198 | - Manage scope, deadlines, and deliverables |
|||
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 199 | |
| 175351 | Nikhil | 2025-10-09 09:01:26 | 200 | > ## Future Roadmap |
| c27abc | Sakshi Mahajan | 2025-11-17 06:39:47 | 201 | |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 202 | |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 203 | If this project continues, here are the strategic next steps: |
| 204 | #### Short-Term Goals (0–2 months) |
|||
| 205 | ||||
| 206 | - Increase sentiment prediction accuracy. |
|||
| 207 | ||||
| 208 | - Improve noise filtering and source credibility scoring |
|||
| 209 | ||||
| 210 | - Enhance Flutter UI for smoother live chart rendering |
|||
| 211 | ||||
| 212 | - Optimize ingestion pipeline for faster turnaround |
|||
| 213 | ||||
| 214 | - Begin analysis of additional news resources, sources, and feeds to expand coverage |
|||
| 215 | ||||
| 216 | #### Medium-Term Goals (2–6 months) |
|||
| 217 | ||||
| adfaec | Sakshi Mahajan | 2025-12-12 05:58:52 | 218 | - Launch the Sentify Mobile App (Flutter) publicly![]() |
| bfb362 | Sakshi Mahajan | 2025-11-18 06:10:23 | 219 | |
| 220 | - Add multi-source comparative analysis (impact ranking from different news outlets) |
|||
| 221 | ||||
| 222 | - Introduce custom user alert rules (coin-specific, FUD alerts, volume spikes, etc.) |
|||
| 223 | ||||
| 224 | - Build a web-based analytics dashboard for historical sentiment |
|||
| 225 | ||||
| 226 | - Expand ingestion to niche crypto sources (DeFi blogs, GitHub updates, developer notes) |
|||
| 227 | ||||
| 228 | #### Long-Term Goals (6+ months) |
|||
| 229 | ||||
| 230 | - Build an Admin Web Application for controlling ingestion pipeline, users, source management, and system monitoring |
|||
| 231 | ||||
| 232 | - Introduce automated trading signal suggestions based on long-term sentiment patterns |
|||
| 233 | ||||
| 234 | - Add multilingual news support for global coverage |
|||
| 235 | ||||
| 236 | - Deploy an enterprise API for institutional users and trading firms |
|||
| 70fa0a | Sakshi Mahajan | 2025-11-28 11:13:18 | 237 | > ## Repository |
| 96aeda | Sakshi Mahajan | 2025-11-18 06:15:37 | 238 | |
| 239 | * **GitHub Repository:** [Sentify (Gitlab)](https://gitlab.enovate-it.com/enovate/hackathon/sentify) |
|||
| 240 | ||||
| adfaec | Sakshi Mahajan | 2025-12-12 05:58:52 | 241 | > ## Demo URL |
| 242 | ||||
| 243 | 🚀 Team Apex is ready for launch! |
|||
| 244 | ||||
| 245 | Our goal? **Turning News-Based-Sentiment into Crypto Certainty.** 📉 ➡️ 📈 |
|||
| 246 | ||||
| 247 | Grab the APK below to try it out on your device. We’d love for you to have it installed so you can experience the features. |
|||
| 248 | ||||
| 249 | [Download the Senity application](https://drive.google.com/file/d/11U5oqRpOG6GN6RJk_cBqEZX4jI7q-M_I/view?usp=sharing) |
|||
| 250 | ||||
| 251 | ||||
| 252 | > ## Screenshots |
|||
| 253 |  |
|||
| 254 |  |
|||
| f987c6 | Nikhil | 2025-10-09 10:17:03 | 255 | |
| fe0514 | Sakshi Mahajan | 2025-09-24 10:25:33 | 256 | |
| 257 | **Categories:** #project #ai-hackathon-[year] #category-[your-topic] |