{"id":31208652,"url":"https://github.com/parth1899/artha-yukti","last_synced_at":"2026-04-27T16:32:02.151Z","repository":{"id":281340021,"uuid":"940955558","full_name":"parth1899/Artha-Yukti","owner":"parth1899","description":"A deep learning platform that combines FinBERT-based sentiment analysis with LSTM-driven stock forecasting, delivering real-time, API-powered financial insights with confidence scoring.","archived":false,"fork":false,"pushed_at":"2025-09-18T12:01:59.000Z","size":141198,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-18T14:33:45.431Z","etag":null,"topics":["finbert","flask","lstm-neural-networks","react","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/parth1899.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-03-01T06:08:21.000Z","updated_at":"2025-09-18T12:02:04.000Z","dependencies_parsed_at":"2025-09-18T14:44:09.042Z","dependency_job_id":null,"html_url":"https://github.com/parth1899/Artha-Yukti","commit_stats":null,"previous_names":["parth1899/financial-sentiment-analysis-and-stock-forecasting-platform","parth1899/artha-yukti"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/parth1899/Artha-Yukti","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/parth1899%2FArtha-Yukti","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/parth1899%2FArtha-Yukti/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/parth1899%2FArtha-Yukti/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/parth1899%2FArtha-Yukti/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/parth1899","download_url":"https://codeload.github.com/parth1899/Artha-Yukti/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/parth1899%2FArtha-Yukti/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276179882,"owners_count":25598571,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-20T02:00:10.207Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["finbert","flask","lstm-neural-networks","react","tensorflow"],"created_at":"2025-09-21T00:44:24.827Z","updated_at":"2025-09-21T00:44:32.844Z","avatar_url":"https://github.com/parth1899.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Learning-Driven Financial Sentiment Analysis \u0026 Stock Forecasting Platform\nBuilt for INDOvateAI Sprint 2025 | Secured Second Prize 🏆\n\nThis project integrates FinBERT-based sentiment analysis with an LSTM-based stock price prediction model to provide a comprehensive market analysis. It dynamically assigns weightage to sentiment and price forecasts to improve investment decision-making.\n\n---\n\n## 🚨 Problem Statement  \n\n- **Investors face an overwhelming volume of real-time data, leading to delayed decisions and missed opportunities.**  \n- **Extracting accurate sentiment from unstructured sources is complex and error-prone, posing high-stakes risks.**  \n\n---\n\n## 🛠️ Solution Approach  \n\n- **Custom Nifty50 database (2014–2025, 129,377 rows)** → Cleaned \u0026 preprocessed for time-series forecasting.  \n- **FinBERT-based Sentiment Extraction** → Trained on **1.4M financial headlines** to extract **bullish, bearish, or neutral** sentiment.  \n- **LSTM-based Time-Series Prediction** → Forecasts stock price trends based on historical market data.  \n- **User-Friendly Dashboard** → Displays **prediction charts, source citations, analytics, and investment recommendations**.  \n\n---\n\n## 🎥 Demo  \n\nhttps://github.com/user-attachments/assets/4c9511a8-e48e-4f45-85fd-0fcb628f0f8a\n\n---\n\n## 🏗️ System Architecture  \n\n![architecture](https://github.com/user-attachments/assets/bca71941-0f8e-47dd-8680-df9d8223de0a)\n\n\n1️⃣ **Data Acquisition \u0026 Reliability**  \n   - Customizable ETL from `yfinance` for accurate real-time data.  \n   - Fully documented \u0026 version-controlled codebase on GitHub.  \n\n2️⃣ **NLP \u0026 Sentiment Analysis**  \n   - **Structured LLMs** for multi-language financial news processing.  \n   - Sentiment classification (**bearish, bullish, neutral**) via **FinBERT**.  \n\n3️⃣ **Forecasting \u0026 Dynamic Analysis**  \n   - LSTM-based stock price forecasting.  \n   - Weighted analysis combining sentiment \u0026 confidence scores using a custom formula.  \n   - Provides **actionable insights** for investors.  \n\n4️⃣ **Real-Time Processing \u0026 Scalability**  \n   - Low latency real-time input processing.  \n   - Extensive **Flask endpoints** for API-driven predictions.  \n   - Cache-based state management for multi-user support.  \n\n5️⃣ **Visualization \u0026 User Empowerment**  \n   - Multiple interactive **graph view options**.  \n   - **Source verification** for user confidence \u0026 validation.  \n\n---\n\n## 🚀 Features  \n\n✅ **LSTM \u0026 FinBERT Integration** – Combines deep learning \u0026 NLP for robust stock forecasting.  \n✅ **Sentiment Analysis from Financial News** – Extracts real-time news sentiment.  \n✅ **Custom Dynamic Weight Assignment** – Adjusts importance of sentiment vs. prediction confidence.  \n✅ **Real-Time Market Predictions** – Generates **buy/hold/sell** signals.  \n✅ **Market Analysis Dashboard** – Displays **real-time sentiment, trend predictions, and historical analysis**.  \n✅ **Multi-Market Adaptability** – Can be extended to **crypto, forex, and commodities**.  \n✅ **Research \u0026 Analytics Tool** – Useful for **financial researchers \u0026 institutions**.  \n\n---\n\n## ⚙️ Installation \u0026 Setup  \n\n### 1️⃣ Clone the Repository  \n```bash\ngit clone https://github.com/parth1899/IndovateAI.git\n```\n\n### 2️⃣ Backend Setup  \n```bash\ncd Backend\n\n# Create and activate a virtual environment (Recommended)\npython -m venv venv\nsource venv/bin/activate  # On Windows, use: venv\\Scripts\\activate\n\n# Install required dependencies\npip install -r requirements.txt\n\n# Running the server\npython ./app.py\n```\n\n### 3️⃣ Frontend Setup  \n```bash\ncd ../Frontend\n\n# Install dependencies\nnpm install\n\n# Start the development server\nnpm run dev\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparth1899%2Fartha-yukti","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fparth1899%2Fartha-yukti","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparth1899%2Fartha-yukti/lists"}