IT Professional with 10+ years of experience in Data Engineering, Machine Learning, and Software Development, specializing in big data processing, ETL pipelines, and predictive analytics. Strong expertise in SQL optimization (Oracle, ClickHouse, SQL Server), Python, PySpark, and cloud platforms (GCP). Proven track record in credit risk modeling, real-time analytics, and high-performance database design. Skilled in automating workflows, building scalable data architectures, and deploying machine learning models to drive business insights. Combines technical proficiency with strategic problem-solving to deliver efficient, data-driven solutions.
AD Logistics
January 2025 - Present
• Automated Excel-to-SQL Server data imports for 50+ daily files with data quality checks, cutting manual processing time by 40% • Optimized SQL queries to accelerate report generation speed by 80%, reducing average runtime from 15 minutes to 3 minutes • Scaled interactive dashboards (Power BI/SSRS) to 500+ end-users, empowering the Head Quarter with real-time logistics insights and driving strategic decision-making across the organization
DataNest
April 2021 - July 2023
• Managed portfolio performance, monitoring and analyzing campaign effectiveness • Enhanced credit scoring product performance, increased qualified leads by 10% while maintaining acceptable risk thresholds through in-depth data analysis. • Significantly improved operational efficiency by cutting operational training time from 3 months to 2 weeks
DataNest
February 2020 - April 2021
• Composed automated ETL pipelines of 10 billion rows of Telco data daily using Python(PySpark) and Airflow, reducing manual runtime from 10 hours to 2 hours by building an in-house mini decision engine. • Developed and optimized real-time monitoring dashboards (using ClickHouse DB, Redash, and Grafana) tracking over 100 key metrics (including model features, credit/borrow/fraud scores, and match rates) enabling data-driven decisions for 50+ stakeholders
Vietnam International Bank – VIB
February 2019 - February 2020
• Built PD (Probability of Default) model project using Python & logistic regression, boosting accuracy by 20% and ensuring Basel III compliance • Standardized DataMart by consolidating data from 6 core systems, implementing validation rules, and optimizing SQL Server queries, enhancing data accuracy by 40% to support critical business reporting • Automated monthly risk metric reports using SQL Server, reducing delivery time from 2 days to 4 hours • Initiated LOS migration project, reducing manual errors and accelerating loan approval turnaround by 35%
HomeCredit
December 2017 - February 2019
• Managed the end-to-end Cross-Sell auto approval process by researching and developing strategies that minimized risks and maximized eligibility and profit through the application of a Risk-Based Model over a Flat Model. • Developed and deployed a predictive credit risk PD model using SAS Miner and Python, leading to a 6% reduction in overall risk. • Trained and coached 5 team members to ensure high-quality task outcomes, focusing on Oracle SQL, LISP Miner, SAS Miner, credit scorecard methodologies, and risk analysis techniques. • Designed a real-time Tableau dashboard for monitoring KPIs (credit scores, fraud scores, approval rates), which reduced manual reporting and enabled quicker risk mitigation decisions for over 20,000 daily loan applications. • Conducted A/B testing to assist the marketing team in identifying optimal sales strategies while controlling risk, targeting clients with high loan potential and low risk.
HomeCredit
February 2016 - December 2017
• Optimized data processing by transforming a 10,000-line SQL Server code from manual execution to an automated Oracle procedure, reducing runtime from 7 hours to 30 minutes by leveraging Oracle partitioning, hints and parallel processing, while ensuring 100% data correctness. • Constructed a Credit Risk Data Mart model to enhance predictive modeling capabilities, streamlining the risk report preparation process for a 30-member risk analyst team. • Provided training to the team on SQL technical skills and risk analysis methodologies, fostering improved technical proficiency and analytical capability.
HomeCredit
November 2013 - February 2016
• Produced complex ad-hoc reports through quantitative analysis, utilizing data segmentation and analysis tools like LISP Miner, SAS Miner, Excel, Tableau, and PowerBI to detect risk anomalies. • Set up and adjusted strategies with decision engines (Blaze Advisor) by implementing hard and soft checks to control risk, ensuring approval rates were aligned with the sales team while maintaining risk under control. • Conducted A/B testing to identify optimal risk strategies. • Enhanced data quality and monitored portfolios (Acquisition and Cross-sale) using risk KPIs (FPD30, FSTPD90, etc.)
Navibank Card Center
March 2011 - October 2013
• Support IT infrastructure and operations for the Card Center (website, database, network), including maintenance planning, system backups, and reporting, while managing 40 ATMs and 400 POS terminals. • Developed new functionalities and services for card systems, ATMs, and POS terminals, including adding PIN change on POS and integrating systems with SMS and middle gateways to enhance security and reduce modification costs. • Engineered and optimized high-availability database and transaction systems, achieving 99% uptime to support over 1 million daily transactions for financial services. • Developed a VisaNet-integrated financial gateway (Oracle/C#, ISO8583) that reduced third-party dependencies by $80K annually and processed over 200 financial transactions per second.
HUT - Ho Chi Minh University of Transport - Vietnam, September 2004
Computer Science
Oracle
Issued: 1/1/2025
Credential ID: 81108DC6CD8B0855C75FFD2B364E64B2470EC8C1AE75DBD42C5AEC9F3854AD8F
Udemy
Issued: 11/1/2024
Credential ID: UC-c12e1449-f42d-45f3-9263-23dc2677c7c5
Verified Data Engineer
8+ years of experience
Preferred commitment: Full Time
Take the next step and bring this top talent to your team
Hire Anh for your team