Provide technical innovations to accelerate data science models to the cloud. Assist data scientists to deploy trained models to REST API, integrating with model governance. Design and maintain CI/CD pipeline. Integrate templates for best practices , hosted documentation and code testing.

Crop science data scientist working on data pipelines from database design to deployed statistical models. I am responsible for building and maintaining our teams data infrastructure, particularly for cloud services in AWS, including relational databases and non-relational databases, and data pipelines. The infrastructure is deployed by using AWS and the data transformation through Python and R. Predictive model REST API hosted using API-Gateway from Sagemaker. Model lifecycle tracking using MLflow. I collect, understand, clean, analyze, integrate and investigate data. Representing the challenges of the project through mathematical models. Formulate and test hypotheses. Discover correlations/relationships of data to support measurement. Identify the right display models according to the challenges of the project and data sets.

I have provided technical services to 12+ stores across New England by updating segment results. I have developed and implemented methods to complete project operations as well as determined technical requirements for analytic solutions development. I have conducted various analysis and designed report charts through utilisation of HTML notebooks, such as Jupyter and R-markdown. I have examined data string as well as created and standardised data features. I have selected and deployed perfect multi-processing and parallel computing resources. I have performed several operations such as assessing principal component, ensuring customer satisfaction, providing suggestions for improvement, and validating reliability for each clustering algorithm. Key Achievements:► Planned and introduced metrics tracking customers/revenue, including customer acquisition cost, customer lifetime value, customer average spending, and customer average frequency.► Implemented technologies, comprising bootstrap, cross validation, and ensemble model results that enhanced the efficiencies of clustering algorithm.► Executed forecast R framework for sales revenue predictive modelling to streamline sales processes.► Leveraged technical skills to use plotly (Python) and shiny (R) to provide dynamic charts and dashboards.► Supported PostgreSQL database and designed MySQL setup through automation of curated data updates.► Developed prototype of clustering machine learning algorithm which demonstrates that a design concept.► Optimized low bias and high variance trade in order to achieve desired performance.► Evaluated processes by executing business performance metrics, which resulted in improving sales revenue and customer experience.

Analyze restaurant point of sale transactions to extract customer and sales data. Query data from API and continuously update data from a medium sized, e.g. 10+ restaurant chain. Cluster algorithms and models are used to model customer spending behavior. The resulting cluster segments were used to drive marketing campaigns. Model results and tools were made available to a non-technical audience . Weekly updates with client to ensure progress meets expectations.

I have directed and co-ordinated with data vendors providing proprietary data. I have operated and administered relational data bases/API’s, such as HADOOP (HDFS, Spark), MySQL, and PostgreSQL. Identified business needs and designed app for airline travel using historical/current ticket price. I have implemented physical and virtual component of limited availability within a computer system. I have deployed, managed, and controlled virtual environment for isolating automated forecasting software. I have carried out various operations such as integrate R to python, optimizing models for stock forecasting, directing team of developers, and profile computational efficiency. I have formulated airline forecast reports on monthly basis, conducted quality audits, and submitted to client.Key Achievements:► Ensured the accuracy of software while conducting software by collaborating with potential clients to demonstrate automated forecasting tools.► Isolated computational inefficiencies in software on time and outlined priority assignment for developers.► Launched production ready forecast models by using python, scikit-learn, and R forecast and caret.► Developed real time streaming UI for big data files such as Hadoop and Spark.

Maintain a library of on-demand reports and schedule automatic distributions for stakeholders and executives. Data management for marketing and IT. Organize and present PPM evaluation.

Work with students enrolled in undergraduate mathematic/statistics classes to enhance the learning experience. The majority of my time was spent supervising lab classes and grading papers. I also maintained separate office hours for tutoring. While working I was responsible to report to the department chair and class professor.

In home support for high school age students with courses in physics, mathematics, statistics, and chemistry.

As a student research analyst I focused on cancer biology using Osteopontin as a putative cancer marker. In Dr. Ng’s lab cellular models were analyzed using mono-clonal antibodies, electrophoresis, western blot, ELISA, recombinant protein, and column chromatography. Quantitative analysis was conducted using regression techniques.

IT support for students and faculty. Assisted with a broad range of computer and hardware troubleshooting. Instructed students in the use of Excel for their past due assignments.

Directed a remodel construction company with an annual gross budget in excess of $100,000. Job duties included coordinating subcontractors to maintain appropriate schedule for the client, bookkeeping, inventory controll, customer relations, carpentry, and design.