John Hammerschlag

💼 Professional experience

Agilytic

• Data pipelines design and implementation of a Data Platform on Azure, for reporting and advanced analytics use cases.
• Created a webapp using Streamlit for data cleaning with direct interaction with an Azure Database.
• Developed a time series algorithm for sales forecasting using Prophet and Darts.
• Technologies used: Azure Data Factory, Azure Data Lake, Databricks, Pyspark, Streamlit, Prophet, Darts

• Developed a lead scoring algorithm to find potential new “good” clients exploiting BNB and BCE data using Scikit-Learn.

• Build and design data pipelines on AWS for a reporting data platform.
• Put in place interconnectivity between different AWS accounts to perform the ETL process.
• Employed a delta strategy for specific tables assigned by the client.
• Technologies used: AWS S3, VPC, Secrets Manager, Databricks, PySpark, SQLAlchemy.

N Brown Group

• Developed a Recommender System prototype based on implicit data from purchase data.
• Technologies used: Python, SQL, NumPy, Pandas, Plotly, Scikit‑learn, Matplotlib, Scipy, JupyterLab, AWS Sagemaker, AWS Athena.

🦾 Certifications, trainings

Methodologies

• Data processing, analysis, modelling & visualization
• Product recommendations
• Machine learning
• Clustering and Classification

Software & programming

• Python (incl. Pandas, Numpy, Scipy, Scikit, NLTK)
• Pyspark, Databricks
• SQL
• SageMaker
• MySQL
• Tableau
• Git

Certifications

• Microsoft Certified: Azure Data Engineer Associate (DP203)
• Databricks Certified Data Engineer Associate
• Academy Accreditation - Databricks Lakehouse Fundamentals
• Create Machine Learning Models in Microsoft Azure – Coursera
• Microsoft Azure Machine Learning for Data Scientists – Coursera

🎓 Academic credentials

• MSc in Data Science Lancaster University, 2022 Distinction
• Data Science Bootcamp BrainStation, 2021 (online)
• Data Science with Python Track Datacamp, 2021
• Bachelor’s in Telematic Systems Engineering USMA, 2020 Cum Laude

🇺🇳 Languages