Senior Data Scientist

• Sep 2023 - Present

Data Expert

• Sep 2022 - Feb 2023

Data Scientist

• Jul 2019 - Jun 2022

- Designed and deployed NLP machine learning pipeline in Google cloud platform to predict beverage items on a restaurant menu with 85% accuracy. - Ideated and productionized scalable databases (SQL/NoSQL) that power all Overproof’s products- including GCP training data, using Postgres and MongoDB. - Collaborated with data engineers and data analysts to implement ETL processes on Airflow, optimized SQL queries on Postgres and reduced run time by 80% to perform data extraction that fit analytical requirements. - Coded custom elastic search queries on SQL data with ELK stack and productionized a product search API on the Overproof Application (customer facing) - Developed time series metric dashboards for internal stakeholders to evaluate product performance and drive improvements. Show less

Research Associate

• Feb 2018 - Jul 2019

• Analysed and restructured 1.5 million data records for pattern recognition using Python and Tableau which helped Department of Child Safety to reduce rate of kids entering foster homes by 6%. • Administered algorithms for string metrics in R, resulting in a matching accuracy of 92%; additionally, logistic regression was performed on data provided by the Maricopa County Juvenile Court data. • Performed feature engineering and A/B testing to successfully support practices implemented on foster kids. • Organized Survival Analysis and built an ARIMA model in R to study the annual re-entry of children into congregate care . • Formulated mathematical models like propensity score matching on intervention groups of children with those in a non-interventional group to aid the center’s interview selection process. • Generated reports and visual representations of analysis such as heat maps and plots using TABLEAU, ggplot and R shiny framework. Show less

General Manager

• Jul 2016 - Jun 2017

• Spearheaded the 35 member team in bleaching and finishing units on shop floor. Met aggressive production and safety goals while minimizing equipment downtime using 5S methodology, Root Cause Analysis, Kaizen and Continuous Process Improvement activities. • Evaluated data from control charts for continuous improvement activities, and provided updates to the SQDC board. • Modified machine material batching after run-time, allowing improvements in KPIs such as 10% increase in machine utilisation. • Reviewed budgeted versus actual cost consumption of chemicals in Stenter machine. Extracted data from SAP and analyzed variations using Excel. • Bestowed “Best Team Player” award by the company for standardizing the process route of sample fabric and reducing holding cost margin by 2%. • Fulfilled inspection duties on incoming fabric with Quality lab, and verified the physical inventory against SAP. Show less