•Designed and implemented a data-driven, knowledge-based framework in Python3 for classifying root causes of any inefficiencies in the Amazon’s warehouse system using K-Means Clustering and dynamic statistical analysis.
•Deployed the framework end-to-end in a development pipeline using Native AWS services, including Lambda Functions, ECS, Athena, S3 and etc.
•Deep dived to identify where inefficiencies could occur by collaborating with multiple teams, and built an automated data aggregation model using SQL for extracting and aggregating features relevant to these inefficiencies.
•Conducted extensive data science research for data exploration, and applied techniques such as scaling, PCA (principal component analysis), and various machine learning algorithms.
