Shaik Riyaz’s Post

Hey LinkedIn community! 👋 We've developed an AI model to classify SMS messages as spam or legitimate using advanced techniques like TF-IDF and word embeddings, paired with classifiers such as Naive Bayes, Logistic Regression, and Support Vector Machines. Excited to share how we're leveraging AI to enhance message filtering and user security. Let's connect to discuss more! #SpamDetection #AI #MachineLearning #DataScience #CodSoft @CodSoft Github : https://lnkd.in/gV4a9hQK

🚀 Excited to share my latest project on SPAM SMS Detection! 📱🛡️ In this project, I built a robust AI model capable of distinguishing between spam and legitimate SMS messages. Leveraging advanced techniques such as TF-IDF and word embeddings, coupled with powerful classifiers like Naive Bayes, Logistic Regression, and Support Vector Machines, the model demonstrates high accuracy in identifying spam messages while ensuring genuine messages are not flagged incorrectly. By harnessing the power of machine learning, we can enhance user experience, prevent unwanted disruptions, and prioritize communication security. Check out the screen recording of the project to see the model in action and learn more about the process behind creating this efficient spam detection system. #CosSoft #MachineLearning #DataScience #AI #SpamDetection #SMS #TechInnovation

Hey connections!! Spam Slayer Unlocked💪!Conquered Task 4(SMS Classification) at CodSoft : Building an AI model to detect those pesky spam SMS messages! 🥳 Leveraged the power of TF-IDF & word embeddings alongside classifiers like Naive Bayes & Support Vector Machines.✨ Huge thanks to the CodSoft team for the guidance and support .🥹 Stay tuned for a deeper dive into the model's secret sauce! #internshipachievement #spamdetection #AI #codsoft #machinelearning #communicationsecurity

🚀 Successfully developed an AI model for spam SMS detection! Utilizing TF-IDF and word embeddings, I experimented with Naive Bayes, Logistic Regression, and SVMs to classify messages. Big thanks to CodSoft for their support and guidance! #MachineLearning #SpamFilter #Codsoft

🚀 Excited to Share My Latest Project! 🚀 I’ve developed an "SMS Spam Detection model using Machine Learning" to classify messages as spam or legitimate. Leveraging techniques like TF-IDF and word embeddings, combined with classifiers such as Naive Bayes and Logistic Regression, this project aims to enhance the accuracy of spam detection in SMS messages. 🔍 Project Highlights: Feature Extraction: Used TF-IDF and word embeddings to transform SMS text data into usable features. Classification: Applied Naive Bayes and Logistic Regression to distinguish between spam and legitimate messages. Results: Achieved high classification accuracy, improving the ability to filter out unwanted messages. CodSoft #MachineLearning #SpamDetection #TextClassification #NaiveBayes #LogisticRegression #DataScience #AI

TASK-1 🎉 Excited to share that I've just completed my SMS Spam Classification Project! 🚀 This project involved building an AI model to classify SMS messages as spam or legitimate. I utilized techniques like TF-IDF for feature extraction and classifiers such as Naive Bayes and Logistic Regression to achieve accurate predictions. Throughout this project, I learned the importance of feature engineering and the effectiveness of different classification algorithms in handling text data. #MachineLearning #AI #DataScience #SpamDetection #CodSoft

Holy Algorithms, LinkedIn! 🦇🤖 As I dive deeper into the world of AI learning, I can't help but feel like the Caped Crusader himself, Adam West's (99% match) Batman. Just like Batman, I'm on a mission to solve the riddles of machine learning and bring justice to data processing! "To the Batcomputer, Robin! , In the spirit of Batman's wisdom: POW! - "Good grammar is essential, Robin." And so is clean code and well crafted prompts! 📝 BAM! - "Some days, you just can't get rid of a bomb." Or a stubborn bug or hallucination – validate, validate and validate! 💣 THWACK! - "Always look both ways, Robin." And always double-check your data inputs! 👀 #AI #MachineLearning #IamBatman

📱Task Complete: Spam SMS Detection using Machine Learning! 🚀 Excited to announce the completion of Task 4,where I developed a machine learning model to classify SMS messages as spam or not, with the goal of improving communication security and reducing unwanted spam. Key achievements: ✉️ **Data Preprocessing** including text cleaning and vectorization 🔍 **Feature Extraction** using techniques like TF-IDF 🤖 **Model Training & Optimization** with algorithms like Naive Bayes and SVM 📊 **Model Evaluation** with accuracy, precision, and recall This project was an excellent deep dive into real-time text classification challenges. 💡 #SpamDetection #SMSDetection #MachineLearning #CodSoft #AI

I just wrapped up a fascinating journey with my Machine Learning project, CrimeCast: Forecasting Crime Categories, and achieved an S Grade with a 95% score! 🏆 In this project, I tackled a classification problem where the objective was to develop a model that predicts crime categories based on features like Location, Date Occurred, Date Reported, Modus Operandi, Current Investigation Status, and more. To achieve the best prediction results, I experimented with various models and fine-tuned them to ensure accuracy and reliability. You can check out project notebook here: https://lnkd.in/ghyQSVZw A big thanks to my mentors Sarthak Khandelwal, and Harsh Gupta who supported me throughout this journey! 🙌 #MachineLearning #DataScience #AI #CrimeAnalysis #Project #Kaggle #DataScienceProjects

🚀 Task 3: Email Spam Filtering 🧠 I am excited to share my third project from the TechnoHacks EduTech Official—Email Spam Filtering! In this project, I built a machine learning model to classify emails as spam or ham (non-spam). Here’s a quick breakdown: - Data Cleaning: I processed a dataset containing thousands of emails and cleaned it to keep only the relevant columns. - Preprocessing: Using techniques like tokenization and vectorization, I converted the text data into a format that the model could interpret. - Model Training: I used a Naive Bayes classifier, which is known for its effectiveness in text classification problems. - Evaluation: The model’s performance was evaluated using accuracy and precision, showing promising results in detecting spam! A special thanks for his guidance and support throughout the project. #SpamFiltering #MachineLearning #TechnoHacks #DataScience #AI #EmailClassification Sandip Gavit