Ebad K.’s Post

🎉 Thrilled to share another Milestone! 🎉 I’m excited to announce that I have successfully solved all the Array challenges on HackerRank DSA Chapter! 🚀 This journey has been both challenging and rewarding, enhancing my problem-solving skills and deepening my understanding of data structures. A big thank you to the HackerRank community for providing such valuable resources! Looking forward to tackling more challenges and expanding my skills even further! 💪 #HackerRank #DataStructures #Array #ContinuousLearning #CodingJourney #opentowork #Programming

🌟 Day 25 of 100-Day Data Structures Challenge 🌟 Today, I tackled problem "Longest Palindrome". The task was to find the length of the longest palindrome that can be built from a given string. This challenge involves handling both uppercase and lowercase letters distinctly, as "Aa" is not considered a palindrome. Excited to keep progressing! #100DaysOfCode #Day25 #DataStructures #CodingChallenge #LeetCode

In my recently completed semester at University🏫, I studied #Data_Structures using #C++ under the guidance of Muhammad Ateeq. He put in great effort to clarify all the concepts, and I thoroughly enjoyed learning from him. We covered a lot of concepts like: -) Arrays -) Dynamic Arrays(Vectors) -) Linked lists (singly, doubly, circular) -) Stacks -) Queues -) Trees (Binary Trees, Binary Search Trees, Ternary Trees) -) Graphs -) Hash Tables -) Sorting algorithms (Quick Sort, Merge Sort, Selection Sort, etc) -) Searching algorithms (binary search, linear search) Now, I have started practicing on #HackerRank. 🎉 Excited to share that I've successfully completed the Arrays challenges on HackerRank 🌟 Challenging myself to solve problems and diving deep into data structures has been an incredibly rewarding journey. Every line of code brings new learning and joy, and I'm looking forward to tackling more challenges ahead. #CodingJourney #HackerRank #DataStructures #KeepLearning #Arrays

🚀 Thrilled to share the latest milestone in my "Bank Customer Churn Prediction" project journey! 🏦📊 🔹 Model Training: Leveraged the power of a RandomForestClassifier to build a robust model for predicting customer churn. The model was trained on the preprocessed data, ensuring high accuracy and reliability. 🔹 Model Persistence: After successful training, the model was saved for future predictions and analysis. This step ensures reproducibility and ease of deployment. 🔹 Model Evaluation: Implemented a comprehensive evaluation framework to assess the model's performance using key metrics such as accuracy, precision, recall, and the confusion matrix. 🔹 DVC Integration: The entire model training and evaluation pipeline was seamlessly integrated with DVC for version control and tracking of experiments. This integration ensures that all changes are tracked, and models can be easily compared.[dvc remote](https://lnkd.in/g9HActWi) 🔹 GitHub Repository: Explore the latest updates on model training and evaluation in the project's GitHub repository. Contributions and feedback are always welcome! 🔹 Special Thanks: A heartfelt thank you to Nitish Singh, Pranjal Yadav, and CampusX for their continued support and guidance. Your insights have been instrumental in shaping this project. Stay tuned for more updates as I progress towards model deployment and the development of the prediction app! 📉💻 Check out the project on GitHub for the latest updates and code contributions: [GitHub Repository](https://lnkd.in/d9aYdaCj) #Banking #DataScience #MachineLearning #DVC #GitHub #ChurnPrediction #LinkedInPost #ModelTraining #ModelEvaluation #RandomForest

🚀 Exciting Announcement! 🚀 I am thrilled to share my latest project, a Credit Card Fraud Detection system, which I've developed and just uploaded to my GitHub repository. 🌐💳 This project marks my second foray into the realm of machine learning, and it's been an incredible journey of learning and growth. Leveraging a dataset from Kaggle, I employed a Support Vector Machine (SVM) with a linear kernel to achieve an impressive 96% accuracy in identifying fraudulent transactions. The project highlights my dedication to mastering not only the intricacies of machine learning algorithms but also the importance of data preprocessing, feature engineering, and model tuning. I invite you to explore the project on my GitHub repository and I welcome any feedback or collaboration opportunities. Let's continue pushing the boundaries of what's possible in the world of data science and machine learning! LINK:https://lnkd.in/gcvEBr_e 🌟👩💻 #MachineLearning #DataScience #CreditCardFraudDetection #GitHub #DataAnalytics #SVM #TechInnovation

Today, I delved into the realm of Apache Arrow DataFusion Comet, a project brimming with potential. For teams entrenched in the open-source Spark ecosystem, Comet could be a game-changer. This plugin not only accelerates Spark jobs but also optimizes resource utilization, enhancing overall efficiency. Comet ingeniously swaps out Spark's conventional JVM-driven execution engine with DataFusion, while preserving its overarching execution framework. DataFusion's choice of Rust, a performance-oriented language, empowers it to deliver blazingly fast performance. Comet's emergence aligns with a broader trend of JVM-alternative solutions gaining traction. Databricks pioneered this shift with Photon, opting for C++ to overhaul the execution engine. Both Comet and Photon breathe new life into Spark, revitalizing its capabilities while retaining its robust distribution features. Kudos to the Apple engineers for crafting and open-sourcing Comet, providing a viable alternative to the proprietary Photon. #dataengineering

Sharing My Experience with Break Into Data, Meri N. A month ago, I saw a LinkedIn post about a 30-day data science challenge, and I signed up. After a few days, I received a list of 100 tech professionals to start working with and build a product. I connected with a few, shared insights, and formed a team called Submarine. We focused on building robust fraud transaction detection models for banks using a highly imbalanced dataset (1% fraud). I worked on: - Data exploration and visualization - Removing redundant, highly correlated features by reducing multicollinearity - Building automated data processing pipelines - Most importantly, implementing undersampling techniques to overcome the highly imbalanced dataset I built, trained, and fine-tuned classification models, evaluating them with cross-validation and f1-score, prioritizing recall to minimize missed fraudulent transactions (False Negatives). Collaborating with Soumiya Chadha, Kritika Javali, and Victoria Correa Andrade (from Microsoft) was an excellent experience. I enjoyed and learned a lot. 📝☀️ Fine-tuned logistic regression model accurately identified 91% of fraud transactions. Check out the code on GitHub: https://lnkd.in/gwQXEm4J PS1: Interested in gaining team experience and improving your communication skills? Join the next challenge! PS2: Feedback? It’s very welcome! 💬💬

I'm vacationing and was working on a sandbox #dbt data environment that I can use to play around different orchestration options and of course #DuckDB. Check out the comments for the links to the repos. This was pretty fun (check out the links) and I've learned quite a couple of things while setting this up, so I thought I'd share a couple of them. For instance, I wanted to generate an ERD diagram of the model, so I've asked #chatgpt to generate a Mermaid Chart definition using the contents schema.yml file. Then, I was able to generate the below ERD. I've also seen that it's possible to directly generate the Mermaid definition for the ERD diagram directly in a SQL query 😁

Get ready for the future: Amazing new ways to move data are coming! Explore the incredible tech advances that will change how we transfer data. Join us for the ride into tomorrow! 🌐✨ #datatransfer #techinnovation #futuretech #revolutionarytechnology #innovation #5gtechnology #quantumtechnology #lifi #teched #softwaredevelopers #programmer #digitalfuture #cuttingedgetech #progress #TWJ #TheWebJobs