On a daily basis I work with advanced statistics, data analytics, predictive modeling, causality and A/B Testing. Below is the list of selected frameworks, models and algorithms, that I used in practice and have a strong experience and expertise in:
programming languages such as Python (incl. sklearn, numpy, pandas) and R (incl. tidyverse, dplyr, ggplot2); proficient in 5-10 most popular libraries
SQL, Presto, Spark, Snowflake and Bash to access data and build ETL (data engineering) pipelines and Keras or Tensorflow for Deep Learning solutions
unsupervised learning methods for clustering and dimension reduction (PCA, k-Means, (h)dbscan, tsne, umap) to perform exploratory data analysis, feature engineering and selection
econometric and ML supervised learning models based on ordinary least squares, logit, probit, k-NN, SVM, Decision Tree Models with ensembling (Random Forest) and boosting (XGBoost), Time Series Models and NLP Models
capable and comfortable in driving models into production and deployment stage using MLOps or web frameworks (Flask, Shiny, Rmarkdown)
planning the testing and drawing out-of-sample, out-of-time conclusions through e.g. A/B Tests and XAI (explainable AI and ML)
made with .Rmd and by Kamil © .