Hi, I'm Syahrul Azka
Artificial Intelligence/Machine Learning & Data Science
Transform data into valuable insights and build intelligent AI/ML models to enhance decision-making.
Transform data into valuable insights and build intelligent AI/ML models to enhance decision-making.
I am a data scientist & analyst with a strong background in mathematics and statistics, dedicated to transforming complex data into meaningful insights and intelligent solutions. By combining analytical thinking with a deep understanding of patterns and trends, I develop AI-driven systems that optimize processes, enhance decision-making, and drive innovation. I believe that data is more than just numbers—it tells a story, uncovers hidden opportunities, and has the power to shape the future in impactful ways.
View CV
Managed and developed internal employee and mitra datasets using MySQL, integrated data across multiple tables with Python and SQL joins, performed data preprocessing to produce analysis-ready datasets, and built demographic dashboards in Microsoft Excel and Metabase to support internal reporting and data-driven decision making..
Analyzed customer chat logs to identify recurring questions and enhance the chatbot knowledge base. Built dashboards to monitor complaints during peak periods and conducted retention analysis to support targeted campaigns. Implemented a real-time data pipeline between databases, automated complaint classification using internal LLMs, optimized SQL queries for reporting, and created Excel-based scorecards for customer service teams.
Automated web scraping using Python, Selenium, and BeautifulSoup to extract structured data from dynamic web pages, significantly reducing manual collection time. Collaborated with cross-functional teams to build and maintain efficient data workflows for AI-powered regulatory analysis. Used Git for version control and coordinated development with multiple contributors to ensure clean and collaborative code practices.
Designed and developed a 10-node cluster computing system for distributed processing using Apache Spark and OpenMPI, optimized for big data and machine learning workloads. Delivered a cost-efficient, portable, and energy-efficient infrastructure for educational use in Big Data and AI learning. Documented system architecture, deployment steps, and performance benchmarks to ensure reproducibility and scalability in academic environments.
Developed a face recognition–based attendance system using FaceNet, Python, OpenCV, and DeepFace, integrated with a SQL database for data storage. Built a Streamlit web interface for real-time face verification and automated attendance logging. Deployed and tested the system in an office environment, improving tracking efficiency and reducing manual input errors.
Jakarta, Indonesia
syahrulazka91@gmail.com