Data Scientist | Problem Solver | Tech Enthusiast

🎯 Passionate about turning data into impactful insights and leveraging technology to drive innovation. With a strong foundation in Information Systems, my journey has led me through diverse experiences in banking, data analytics, and cutting-edge machine learning.

• 🎓 Educational Achievements:

  • Cum Laude Graduate in Information Systems (GPA: 3.73) from Tarumanagara University.
  • Recent graduate of the Data Scientist Bootcamp at Hacktiv8 (Score: 88/100).

• 🛠 Professional Experience:

  • Managed banking applications and databases at Bank Sahabat Sampoerna, ensuring smooth operations and high performance.
  • Collaborated on data-driven solutions during my Data Analyst Apprenticeship at Generasi Gigih 2.0 by Yayasan Anak Bangsa Bisa.

• 🏆 Awards & Competitions:

  • 🌐 Delegate of the World Health Organization at the Asia World Model United Nations Virtual Conference.
  • 🥈 2nd Place Winner in the Business Pitching Competition (PMN UNTAR 2021).

• 📈 Projects I’m Proud Of:

  • NLP-Driven Sentiment Analysis for BRImo Reviews Using Transformers with Hugging Face
    Face to classify BRImo Google Play Store reviews into positive, neutral, and negative sentiments.
    Tools: Python, TensorFlow, Hugging Face Transformers.
    Algorithm/Method: IndoBERT (Phase 1 - uncased), Transformers, AdamW Optimizer, Categorical Cross-Entropy Loss.

  • Predicting Loan Defaults: A Comparison of Machine Learning Algorithms
    This project compares the performance of various machine learning algorithms—KNN, SVM, Decision Tree, Random Forest, and XGBoost—for predicting loan defaults based on customer features. The evaluation is conducted using cross-validation to ensure reliable performance metrics and to identify the most effective model for loan default prediction.
    Tools: Python, Scikit-learn, Pandas, NumPy.
    Algorithm/Method: KNN, SVM, Decision Tree, Random Forest, XGBoost, Cross-Validation.

  • Market Segmentation Analysis for Olist Store with Tableau
    Developed an interactive dashboard to segment Olist's market based on product types, regions, and other key factors, using statistical analysis for accurate market segmentation. The solution utilizes Python for data analysis, Seaborn and Matplotlib for visualization, and Tableau for an insightful and interactive dashboard.
    Tools: Tableau, Python, Pandas, Matplotlib, Seaborn.
    Algorithm/Method: Statistical Analysis.

• Programming Languages:
  
  

• Cloud & Infrastructure:
  
  

• Data Tools:
  
  
  
  
  
  
  
  
  
  

• Databases:
  
  
  
  
  

• APIs & Workflow Tools:
  
  

• Version Control & Collaboration:
  
  
  
  

• Business Intelligence Tools:
  
  
  
  

• Search & Analytics:
  
  

• ETL & Data Integration:
  

• Containerization & Virtualization:
  

• Generative AI and advanced machine learning techniques.
• Exploring ETL processes and big data solutions like Hadoop, Kafka, and other tools to enhance my analytics game.

💼 LinkedIn: Ruach Sakadewa
📚 DataCamp: Ruach Sakadewa
💻 GitHub: rsakadewa7
🤗 Hugging Face: rsakadewa7
🎓 HackerRank: rsakadewa7
📊 Kaggle: rsakadewa7

📧 Email: rsakadewa7@gmail.com
📱 WhatsApp: +62-877-3077-5718