Machine Learning Engineer
Current- Researched and produced updated call transcription and analysis methods for client, using machine learning (Fuzzy Matching, TFIDF, Vectors) in Python to analyze calls in English, Spanish and Mandarin
- Implemented Pandas in Python and PySpark to manipulate, organize, understand, and test large amounts of data and present it to colleagues and the client in data frames, violin plots, histograms, and write ups.
- Consulted senior data scientist and manager to present, learn, and improve on emerging technologies thatcould be used to help the client
- Collaborated with a senior data analyst to update a pipeline for transcriptions in Luigi and Bash, making it more efficient for broader use in the future
- Implemented the capability to prompt a user to choose one of three languages (English, Spanish,Mandarin) to access the data
- Customized the search menu for the CI/CD pipeline to categorize the data by date and topic