Data Science
ML & NLP Experiments
Data Scientist
Series of experiments combining classical ML, topic modelling, and recommendation pipelines. Delivered reproducible notebooks and stakeholder summaries for non-technical decision makers.
Challenge
Stakeholders needed reusable patterns to explore heterogeneous datasets, from text corpora to mobility logs.
Approach
Ran structured experiments combining classical ML, topic modelling, and recommendation techniques with reproducible notebooks.
Outcome
Provided decision-makers with clear playbooks and code templates to accelerate future data initiatives.
Highlights
- Top academic result across deliverables
- Reusable code templates for future teams
- Communicated insights to mixed audiences