Modelling customer behavior and estimating causalities

Modelling customer behavior and estimating causalities

Course Description

This is a practical course based on the most useful and universal ML application use cases from my experience as a consultant and extended with causal modeling topics. 1. Bias in explaining results 2. Modeling the impact of projects on results. Simulation vs Historical ML model tradeoffs 3. Estimating causalities in complex networks ( Telco, Finance, Retail) 4. Pricing with ML algorithms (different pricing strategies and ways to analyze data) 5. Modeling preferences of customers (speed price tradeoff) 6. Customer analytics universal use-cases (CLV, Segmentations, NBA, etc)

Course tools

  • Python(R might be applied if needed)


  • Python, basics of ML
Level of complexity of course Intermediate


Liubomyr Bregman Amazon EU, Data Science Lead Liubomyr is a data scientist, and manager with a focus on causalities, networks, and marketing analytics with experience in eCommerce, financial sector, and telco. Fields of interests: Causal ML, Customer analytics      

Про факультет

Важлива інформація

Контактна інформація