Created and managed a data catalog with clear documentation for easy team access.Data modelling and create physical data model with auto update using Github CI-CD pipeline.Utilized the SAX representation technique to reduce time-series data dimensionality, solving a bottleneck problem that allows complex algorithms and pipelines to run on generic machines 3 times faster on average.

Use ETL tools to build data pipeline for data mart for a big logistics client.Write automated rules using SQL to check for data quality after the ETL process.Apply clustering algorithms to cluster the customers, allowing the client to more efficiently serve their customers using customized Marketing strategy and recommendation system.

Collaborate with engineering and product development teams to propose solutions andstrategies to business challenges. Reduce time to assign responsibility when loss occur by 76% by developing rule for automatic assigning.Design data mart using star schema and build ETL flow for data mart.

Perform exploratory data analysis, including data cleaning, data visualization. Automating the process of queryingdata from REST API and sending report.Deliver PoCs code and integration of machine learning algorithm to segment Viettel Pay e-banking user profiling.Use A/B testing to determine and evaluate the solution to decrease customer churn caused by an error.

Explore consumers’ behaviour data for any inconsistencies and outliers.Visualize data and conduct statistical test for significance Communicate, discuss research findings with team members. Output: an open access dataset and a report for the project.