Speaker

Hristo Hristov

Hristo Hristov

MCSE Data Management and Analytics, Project Engineer at Atlas Copco Airpower

Antwerpen, Belgium

Hristo has an international background in business and analytics. For 7 years he worked at a website engineering consultancy, then he transitioned to a career as an IT business analyst. His current job at Atlas Copco Airpower in Flanders, Belgium has given him the chance to deliver great value with advanced solutions in the analytics, Azure cloud and O365 domains. Hristo’s real passion is predictive analytics and statistical analysis. He holds a Master’s Degree in Data Science and a number of Microsoft certifications covering SQL, PowerBi and related technologies. Pythonista who deeply cares about code comments.

Area of Expertise

  • Information & Communications Technology
  • Business & Management

Topics

  • SQL
  • PowerBI
  • Azure
  • python3
  • Database and Analytics
  • Predictive Analytics
  • Databases
  • Machine Learning & AI
  • Azure Machine Learning Studio
  • SharePoint Online
  • O365
  • Microsoft PowerApps

Categorizing Customers with SQL Server Machine Learning Services

We will use Python to develop and deploy a K-Means clustering model in SQL Server Machine Learning Services to categorize customer data. The session aims at showcasing the built-in machine learning capabilities of the SQL platform.

Categorical Data Encoding for Regression Models

The session explores the usage and comparison of 5 different text encoding techniques: one-hot, target, hashing, binary and entity embeddings. The methods are needed in cases when text data must be represented numerically before used in a predictive model or neural network. A dataset from a support system is used where the aim is predicting case duration.

Hristo Hristov

MCSE Data Management and Analytics, Project Engineer at Atlas Copco Airpower

Antwerpen, Belgium

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top