Data Science: The Technological Aspect

Python, R and SQL:

• Some R libraries I like to use: ggplot, tidyverse, sparklyr, forecast, rstanar, mgcv, zoo, xts, broom, mgcv, rjags
• Some Python libraries I like to use: pandas, pyspark, bokeh, pymc3
• Pricing of secured consumer loans.
• Credit policy of secured consumer loans.
• Forecasting of air-traffic landings, departures and passengers of 20 regional airports in Finland for years 2016, 2017 and 2018.
• Land-traffic emission estimation for an airport operator
• New route load factor estimations for various airlines
• A plethora of experience with data visualization. I am a ggplot wizard.
• Development of a customer flow model for chain of amusement parks
• Net Promoter Score data analysis
• 69 passed R, Python and SQL courses in DataCamp. I've spent a few evenings there since 2015.

Apache Spark:

• A lot of data-wrangling and then some more data-wrangling... and also feature engineering, statistical modeling, machine learning.
• Big Data with PySpark Track, Datacamp certification
• Introduction to Spark in R using sparklyr, DataCamp certification
• 3-day Microsoft hands-on Spark / Databricks Bootcamp

Power BI:

• A lot of BI reports for clients in various industries and for many company functions
• I like to solve things in the Power Query side: A lot of custom function queries not possible with point and click
• Power BI Embedded: Software development with Power BI Embedded
• Certificates are nice, thus I have one for this as well.

Data Science: The Mathematical Aspect

I am an Econometrician by education.

Regression Modeling:

• Multiple Linear Regression, Logistic, Poisson, Dif-in-dif, IV regression, RDD, LOESS - far too many techniques to list here.
• Pricing of mortgages & collateralized debt
• Pricing of airport charges
• Air-traffic passenger forecasts
• Passenger land-traffic emission calculations for Helsinki-Vantaa airport
• Customer flow modeling for a chain of amusement parks in Finland
• Demand forecasting for financial products
• Validation of strategy for a commercial real estate company through a statistical model
• Econometrics (Aalto University)
• Advanced Econometrics (University of Helsinki)
• Applied Microeconometrics I (Aalto University)
• Applied Microeconometrics II (Aalto University)
• Productivity and Efficiency Analysis (Aalto University)
• Continuation Course in Statistics (Aalto University)
• Master's Thesis: Statistical evaluation of macroeconomic forecasting industry in Finland. Grade: 4 (Aalto University 2016)

Bayesian Modeling:

• Bayesian regression, Naive Bayes Classification, Natural Conjugate Models and MCMC
• LDA for Natural Language Processing
• Bayesian Econometrics (University of Helsinki, Doctoral Level Course)
• Bayesian Statistics (Coursera)
• Fundamentals of Bayesian Data Analysis in R (Datacamp)
• Bayesian Modeling with RJAGS (Datacamp)
• Bayesian Regression Modeling with rstanarm (Datacamp)

Time-series Analysis:

• Seasonal Autoregressive Integrated Moving Average with eXogenous regressors (SARIMAX), Vector Autoregression (VAR)
• Air-traffic passenger forecasts
• Time-series Analysis (Aalto University)
• ARIMA modeling in R (Datacamp)

Machine Learning:

• Generalized Additive Model, Random Forest, kmeans, Hierarchical Clustering
• Multiple courses in DataCamp