Data Scientist
Neossys·Jan 2021 - Jul 2022
Data collection and ML modeling for company intelligence: large-scale web scraping, revenue prediction, industry classification, and keyword suggestion engine.
About this role
Neossys is a Luxembourg-based startup that collects, analyzes, and aggregates data on tens of millions of companies across Europe to make it accessible to its clients.
As the sole Data Scientist at Neossys, I was responsible for two main areas: data collection through large-scale web scrapers, and machine learning modeling to enrich the company database with predicted attributes.
The dual nature of the role — spanning data engineering and data science — required both breadth and autonomy, working closely with the product and engineering team in an Agile environment.
Key contributions
- Developed numerous web scrapers to collect company data at scale across Europe (Selenium, Python).
- Built a revenue prediction model to estimate company financials from available signals.
- Developed an industry and business sector classification model.
- Built a keyword suggestion engine to support the platform's search functionality.
Skills
PythonPandasSeleniumFlaskScikit-LearnBitbucketJiraAgile