A data scientist with solid mathematics and statistics background having a master degree in mathematics. Offering twenty plus years experience in software development, build and release engineering, production support of enterprise systems and data science such as mastering data management (MDM), ETL and machine learning (NLP, data mining, anomaly detection). Have demonstrated expertise working with and maintaining open-source data analysis platforms such as Python, R, Hadoop (Hive, Oozie, HBase, Pig, Sqoop, HCatalog), SQL (Oracle, MySql), noSQL (MongoDB), Apache Spark, Spark MLLib and scalable AWS (Amazon Web Services EC2) environment including deep learning libraries like Keras and Google Tensorflow.
Comfortable working with distributed teams in an agile environment on delivering solutions, uses GIT as version control systems and deeply-involved contributor in code/design reviews. Domain expertise includes logistics, supply chain and automotive industries.
Employed by Modis Inc and assigned to Ford Motor Company in Dearborn Michigan, USA from 2017 to present
Responsibilities:
- Drive and enforce master database management(MDM) strategy and data stewardship
- Work on all the data types across the enterprise including Customer, Dealer, Vehicle, Manufacturing and Services
- Provide visibility to Data Quality issues and work with the business owners to fix the issues
- Serve as data subject matter expert and demonstrate an understanding of key data management principles and data use
Orient Overseas Container Lines (OOCL) in San Jose California, USA Inc from 2007 to 2017
- 10 years
Software Engr Data Science (2013 to 2017)
- Identify, analyze and create data feature roadmap
- Develop machine learning algorithms to solve inventory demand/supply problems
- Collaborate with teams from prototyping to implementation of the entire project
- Create and maintain data pipeline that feeds data into a network engine and integrated from an existing system
- Design and build infrastructure for extracting, transforming and loading data from different data sources
Software Release Engineer (2010 to 2013)
- Development of an automated and continuous integration and continuous deployment (CI/CD) using Jenkins / Maven
- Created an automated QA testing scripts for environment auto health checking using QTP
Software Engineer (2007 to 2009):
- Smalltalk developer (2009) for an enterprise system and handles enhancements, maintenance and support.
- Worked as a Production Support Coordinator (2007-2009) and managed remote teams in Manila and Hong Kong.
Global Production Support Team Lead
OOCL Philippines from 1997 to 2007 - 10 years
- Provides 24 X 7 production technical support for Global Enterprise Systems
- Drives team's performance and productivity and analyzes if the delivered solutions meet business requirements.
University of the City Of Manila and
Central Colleges of the Philippines from 1994 to 1996 - 3 years
- Teaches basic and advanced subjects in Mathematics and Statistics
Nov 2017 to May 2018 (7 months)
- Integrate, organize and land data from multiple applications from different sources like mainframe, sql server and third party data into hadoop datalake
- This data replication enables new insights and data science solutions for manufacturing, product development, purchasing and finance
- Provide visibility for monitoring operational data by deploying a predictive model to detect anomalies based on record counts, cardinality and other data quality issues.
May 2018 to July 2018 (3 months)
- Part of SAS retirement project, this project aims to migrate SAS data into hadoop environment and replacing SAS codes into python
- The main consumer of this data is business analytics team working on vehicle product analytics
- Proactively monitor disruptions related to data quality by visualization via a monitoring dashboard
Sep 2017 to Oct 2017 (2 months)
- Create a detailed and precise vehicle descriptions like body model/style, type and make based on data coming from different regional applications
- Reverse engineering of partial vehicle id using the first 11 characters/digits
- Standardize and curated data from vehicle then provide insight on customer behavior, traits and their vehicle performance for maintenance
July 2018
- Create a data pipeline to extract and transform vehicle data from different sources
- This allows analytics team to develop mobility solutions, improve products and customer service
- This also gives fleet managers and service providers access to valuable vehicle data for better management of their fleets
June 2018
- Measure customer likeability and satisfaction on offered Services and Products
- Looks ways to improve customer satisfaction and likeability
- Formulate customer driven marketing strategies for future use
