Telecom Churn Prediction System with FastAPI and Scikit-Learn

🎯 Precision Engineering: Beyond Basic Queries "A great API doesn't just give you data—it gives you the right data, or a clear reason why it can't. 🛡️ Today I expanded my TodoApp by implementing Path Parameters. Moving beyond fetching 'all' records, I’ve added logic to retrieve specific tasks by their ID. Key technical highlights from this update: ✅ Input Validation: Used FastAPI’s Path to ensure only valid IDs (greater than 0) are processed. ✅ Robust Error Handling: Integrated HTTPException to return a clean 404 Not Found status if a user requests an ID that doesn't exist. ✅ Clean Code: Refactored using Annotated dependencies to keep the route handlers lean and readable. Building a backend isn't just about the 'Happy Path'—it's about handling every edge case with precision. Next: Implementing POST requests to allow users to create their own tasks! 🚀" #FastAPI #Python #BackendDevelopment #WebAPI #CleanCode #SoftwareEngineering

🚀 Built a Customer Churn Prediction System Recently worked on an end-to-end Machine Learning project to predict customer churn using a telecom dataset. 🔹 What I worked on: Data preprocessing and basic feature engineering Handling class imbalance using SMOTE Training a Random Forest model Evaluating performance using accuracy, confusion matrix, and F1-score 🔹 Result: Achieved around 93% accuracy, with balanced performance across churn and non-churn classes. 🔹 Deployment: Deployed the model using Streamlit to make it usable for real-time predictions. 👉 Live App: https://lnkd.in/dANr3Dht 👉 GitHub: https://lnkd.in/deFU3xCF This project helped me understand the difference between just building a model and actually making it usable. #MachineLearning #DataScience #Streamlit #Python #EndToEndProject

Just come across this. Another AI agent framework CVE, another reminder that "run this arbitrary code" features are attack surfaces. PraisonAI's run_python() used shell=True with incomplete escaping - $() and backticks slipped right through. The real kicker? The default Flask server ships with AUTH_ENABLED=False, turning a "local" vulnerability into something reachable over the network. AI agents with code execution need the same scrutiny we give to eval() and exec() in web apps.

𝗙𝗮𝘀𝘁𝗔𝗣𝗜 𝗶𝘀𝗻'𝘁 𝗳𝗮𝘀𝘁 𝗯𝗲𝗰𝗮𝘂𝘀𝗲 𝗼𝗳 𝗙𝗮𝘀𝘁𝗔𝗣𝗜.  𝗜𝘁'𝘀 𝗳𝗮𝘀𝘁 𝗯𝗲𝗰𝗮𝘂𝘀𝗲 𝗼𝗳 𝘄𝗵𝗮𝘁'𝘀 𝘂𝗻𝗱𝗲𝗿𝗻𝗲𝗮𝘁𝗵. Most people stop at "FastAPI is faster than Flask." Few ask 𝘸𝘩𝘺. Here's what's actually happening: 𝗙𝗹𝗮𝘀𝗸 runs on 𝗪𝗦𝗚𝗜. One request = one thread = blocked until done.  Your thread waits while the DB responds. It does nothing. Just sits there. 𝗙𝗮𝘀𝘁𝗔𝗣𝗜 runs on 𝗔𝗦𝗚𝗜. One thread handles 𝘵𝘩𝘰𝘶𝘴𝘢𝘯𝘥𝘴 of connections. While one request waits for DB, the thread picks up another. No idle time. But FastAPI doesn't do this alone. The real stack: • 𝗨𝘃𝗶𝗰𝗼𝗿𝗻 — the ASGI server (built on uvloop) • 𝗦𝘁𝗮𝗿𝗹𝗲𝘁𝘁𝗲 — the async engine (handles requests, WebSockets, middleware)  • 𝗙𝗮𝘀𝘁𝗔𝗣𝗜 — the developer layer (validation, docs, type hints) Think of it this way: Starlette = 𝘵𝘩𝘦 𝘦𝘯𝘨𝘪𝘯𝘦. FastAPI = 𝘵𝘩𝘦 𝘥𝘢𝘴𝘩𝘣𝘰𝘢𝘳𝘥.  Uvicorn = 𝘵𝘩𝘦 𝘧𝘶𝘦𝘭. Flask was built for a 𝘀𝘆𝗻𝗰𝗵𝗿𝗼𝗻𝗼𝘂𝘀 world. FastAPI was built for an 𝗮𝘀𝘆𝗻𝗰-𝗳𝗶𝗿𝘀𝘁 world. The speed difference isn't a feature.  It's a 𝗳𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻 difference. Next time someone says "FastAPI is fast", ask them: 𝘐𝘴 𝘪𝘵 𝘍𝘢𝘴𝘵𝘈𝘗𝘐, 𝘰𝘳 𝘪𝘴 𝘪𝘵 𝘚𝘵𝘢𝘳𝘭𝘦𝘵𝘵𝘦? #FastAPI #Flask #Starlette #Python #AsyncProgramming #BackendEngineering #SystemDesign #SoftwareEngineering

Just built my first AI-powered Web Application using Python & Flask! What it does: - Paste any text → AI summarizes it instantly - Paste any text → AI detects sentiment with confidence score All running on a real web interface — not just a notebook! Tech stack: - Python + Flask (backend) - HuggingFace Transformers (AI models) - HTML + CSS (frontend) This is a big step up from Colab notebooks —  building real applications that run on a server. GitHub: https://lnkd.in/dEZguZ3E #Python #Flask #AI #WebDevelopment #HuggingFace #Portfolio

🚀 Building an Automated ML Web App with Streamlit — Now Testing Regression! Last time I showed the app working with a Classification dataset — today I'm back with a Regression dataset and it handles it just as smoothly! 📊 Here's what the app does automatically once you upload your dataset: ✅ Data Preview & Statistical Summary ✅ Univariate, Bivariate & Multivariate Analysis ✅ Automatic Preprocessing (Encoding + Scaling) ✅ Train/Validation/Test Split ✅ Trains 11 Regression Models automatically: Linear, Ridge & Lasso Regression KNN, Decision Tree, Bagging Random Forest, AdaBoost, GBM XGBoost & SVR ✅ Evaluates each model using R2, MAE, MSE & RMSE ✅ Automatically picks the best model based on Validation R2 Score The best part? You just select "Regression" from the dropdown, upload your dataset and the app handles everything from EDA to model comparison — no code needed on your end! 🔥 Previously showed Classification with metrics like Accuracy, F1, Recall, Precision & AUC-ROC — this app supports both problem types seamlessly! Still building — next steps include hyperparameter tuning and model export! 💪 🛠️ Tech Stack: Python | Streamlit | Scikit-learn | XGBoost | Pandas | Matplotlib | Seaborn 🔗 GitHub: github.com/Muskanbanu03 #Python #Streamlit #MachineLearning #DataScience #Regression #BuildInPublic #100DaysOfCode

Tomorrow, 𝗧𝗶𝘁𝗮𝗻𝗫 𝗴𝗼𝗲𝘀 𝗹𝗶𝘃𝗲. Here's what you'll see. 𝐀𝐬𝐤 𝐭𝐡𝐞 𝐃𝐞𝐞𝐩 𝐀𝐠𝐞𝐧𝐭 𝐚 𝐫𝐞𝐬𝐞𝐚𝐫𝐜𝐡 𝐪𝐮𝐞𝐬𝐭𝐢𝐨𝐧. 𝐖𝐚𝐭𝐜𝐡 𝐢𝐭: - Break it into investigation steps - Ask for your approval before proceeding (Human-in-the-Loop) - Search the web, gather data - Stream live progress with visual status updates - Deliver a report with interactive charts, KPI cards, comparison tables — all inline in chat - No matplotlib. No Python scripts. No file downloads. 𝐉𝐮𝐬𝐭 𝐛𝐞𝐚𝐮𝐭𝐢𝐟𝐮𝐥, 𝐢𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐯𝐞 𝐯𝐢𝐬𝐮𝐚𝐥𝐬 𝐫𝐞𝐧𝐝𝐞𝐫𝐞𝐝 𝐝𝐢𝐫𝐞𝐜𝐭𝐥𝐲 𝐢𝐧 𝐭𝐡𝐞 𝐜𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧. Bar charts. Pie charts. Metric grids. Timelines. Gauges. Citations with reliability scores. All from a single prompt. 𝗧𝗼𝗺𝗼𝗿𝗿𝗼𝘄. 𝟭𝟬 𝗔𝗠 𝗖𝗲𝗻𝘁𝗿𝗮𝗹. 🔗 https://lnkd.in/g6XB5AN9 #ProductLaunch #AIDemo #DataVisualization #AGUI

In today’s crowded AI agent space, TitanX’s Deep Agent represents a notable advancement in practical capability. Tomorrow at 10 AM Central, the demo will showcase an agent that: - Decomposes complex research questions into structured steps - Seeks explicit human approval before execution - Performs live web research with visual progress updates - Delivers executive-ready outputs directly in chat, like interactive charts, KPI cards, comparison tables, timelines, gauges, and sourced citations, all rendered natively, without code or exports. This moves beyond text-heavy responses toward true AGUI, potentially accelerating insight cycles for strategy, research, and decision-making teams. Worth attending if you’re evaluating agentic AI for enterprise impact. Drop a comment if you plan to attend, especially if you are interested. 🔗 Original post: https://lnkd.in/gwyM4ZnG #AI #EnterpriseAI #DigitalEmployee #DigitalTwinOrganization #AgenticAI #AIAgents #AISafety #AIOrchestration #LLM #GenerativeAI #Automation #CyberSecurity #IAM #RBAC #ZeroTrust #AIops #MachineLearning #OpenSource #TypeScript #FutureOfWork #AutonomousAgents #AIGovernance #TechInnovation #DigitalTransformation #CES #TitanX #ProductLaunch #BuildInPublic #AIEngineering

🚗 New Car Purchase Prediction using Flask Excited to share my latest project where I combined Machine Learning with Web Development to build a simple prediction app! Project Overview: This web application predicts whether a person will purchase a car based on key inputs like Age and Salary. Technologies Used: ✔️ Python ✔️ Flask ✔️ Scikit-learn ✔️ NumPy & Pandas ✔️ HTML Model Used: ✔️ Decision Tree How it works: ✔️ User enters Age and Salary ✔️ Data is processed by the Flask backend ✔️ Machine Learning model makes prediction ✔️ Result is displayed instantly Key Learning: This project helped me understand how to: ✔️ Integrate ML models with web applications ✔️ Handle user input through forms ✔️ Deploy models in real-world scenarios GitHub : [ https://lnkd.in/gsEcvXHc ] #MachineLearning #Flask #Python #DataScience #AI