Wei Chun Chang User

Revamped the QuickCommerce experimentation framework, boosting A/B testing success rates by 15% and establishing a causal inference framework for vendor-level operational experimentation. Coached Data Scientists and Product teams on leveraging experimentation for product development.

Revamped the experimentation framework, boosting A/B testing success rate by 15% through leveraging past learnings. Established a causal inference framework for vendor-level operational experimentation using Geo test and Synthetic control, while coaching data scientists and product teams on effective experimentation for product development.

Optimized marketplace lifecycle campaigns, lifting contributed sales by 30% for four consecutive quarters through iterative A/B testing and Bayesian inference. Designed a causal inference model to measure incremental campaign value for user segmentation and automated anomaly detection using Tableau Dashboard Alerts. Identified causal relations between features and project lifecycle by analyzing us

Optimized marketplace lifecycle campaigns, lifting contributed sales by 30% for four consecutive quarters through A/B testing and Bayesian inference. Developed a website UI click heatmap tool, saving over 2 hours per test for 100+ A/B tests and enabling better user behavior understanding. Initiated and deployed a recommendation model that increased feature adoption rates by over 10%.

Developed a website UI click heatmap tool, saving over 2 hours of workload per test for 100+ A/B tests and enabling the Dev department to easily understand user behaviors. Initiated and established a design document with a roadmap for development breakdown, including an MVP for collecting feedback. Built an ETL pipeline and collaborated with three different engineering teams for deployment and tes

Contributed to a 52% increase in leads and 68% conversion rate for the Global Selling Seller Summit with the same budget, leading to 35% of next year's sales. Optimized Ads ROI through A/B tests on content development and budget allocation using sentiment analysis by Python.

Initiated and led the development of a Machine Learning Python library for the Rakuten Data Science Department using Python and Git. Reduced the runtime of the ETL pipeline by 15x using PySpark, with the library being adopted by over 30 data scientists company-wide.

Initiated and led the development of a Machine Learning Python library for the Rakuten Data Science Department, significantly reducing ETL pipeline runtime by 15x. This library was adopted by over 30 Data Scientists throughout the company, improving infrastructure understanding and efficiency.

Contributed to a 52% increase in leads with a 68% conversion rate for the Global Selling Seller Summit, maintaining the same budget. Optimized Ads ROI through A/B tests on content development and budget allocation, leveraging sentiment analysis with Python.

Completed a Bachelor of Science degree with a focus on Management Information Systems. Gained foundational knowledge in information technology, business processes, and data management.