Jonathan is a Data and Software Engineer with a high level of proficiency in data analytics, machine learning, and data engineering - producing high-quality, robust, and maintainable products on projects. He also has hands-on experience building 12 cross-platforms iOS/Android games in C++ and self-driving rovers robots with an A* algorithm (desktop+bluetooth). Jonathan develops and implements data models that act as the eyes and ears of complex business solutions.
Delivers data warehouse and ETL solutions as part of an agile team using advanced machine learning techniques to improve performance and processes.
Helps build and improve infrastructure, application and performance development and ensures tight security including data encryption, security groups, and environment scanning.
Ensures high-quality deliverables and implements DevOps and security best practices in fast-paced environments.
Designed and developed propensity models to reduce 70% of cost call center operations. Led the data team to provide actionable insights for clients according to defined business rules and procedures.
Designed Developed SPG fraud detection model, reducing fraud cost by 90% for FMCG clients.
Designed and developed NLU/chatbots for task-based dialogue, open domain, QA, and customer service. Implemented digital analytics platforms to extract and manipulate data from digital sources, Facebook, Google, and SEMRush.
Designed and developed telco apps/packages recommendation systems for 80 million customers. Performed exploratory data analysis, feature engineering and predictive modelling on solutions for Eureka/Indosat.
Built DPI models on telco data, bringing USD 4M new business from the ridesharing industry. Processed terabytes of raw data for the client - updating and maintaining the database.
Scaled fintech models using telco data to 61% gini accuracy with Apache Spark. Acted as first-line support for data platforms within Eureka - maintaining peak operating efficiency and ensuring maximum uptime.
Helped publish a clinical trial article with an NLP model that learns from 152,000 unique conversations. Designed and deployed the analytics platform to enhance clinical trial operations.
Collected, cleaned, managed, and analyzed large sets of data using Tableau to visualize data.
Designed and developed a model to predict participants dropout probability in an ongoing clinical trial study. Worked on the decentralized clinical trial (DCT) platform for clients.
Developed and implemented solutions for data monetization across 2PB, 1TB/day, and messaging data for 80 million customers.
Utilized Spark+Hadoop to transform data from 1TB/day to L2 (customer data, summary statistics, and features).
Divided data into L2 and L3 layers for enhanced analysis and business intelligence.
Education
1. Data Analyst Nanodegree
2. Exploratory Data Analysis, A/B Testing, Machine Learning, Data Science, Data Visualization
Udacity
2016 - 2016
BSc. Computer Engineering
Telkom Institute of Technology, Bandung, Indonesia
2007 - 2012 (5 years)
1. Architecting with Google Kubernetes Engine Specialization
2. Data Engineering, Big Data, and Machine Learning on GCP Specialization
3. Deep Learning Specialization
4. Customer Analytics, Wharton School
5. Executive Data Science, John Hopkins University
