-->

About

Myself

Kaixo! I'm Aritz, a statistician at DCB (Diabetes Center Berne).

My background is in physics and statistics, and I enjoy exploring state-of-the-art statistical- & data science methods. My favorite programming languages are R and Python.

If you keep scrolling down, you will stumble upon some of my projects, as well as more information regarding my background and skills.

Projects

Python

CNN Image Segmentation (bachelor thesis)

The Standard Model of particle physics, while being able to make accurate predictions, has been proved to fail to explain various phenomena, such as astronomical dark matter observations. In this project, a machine learning application is implemented with the goal of studying dark matter candidates. Images from Charge Coupled Devices (CCDs) in different experiments located underground are used to test different deep learning algorithms. A U-Net model is trained with Python's open-source library Keras. The model performs multi-class image segmentation in order to detect dark matter particle signals among background noise.


Original title: Application of deep learning techniques to images collected with Charge Coupled Devices to search for Dark Matter.

Publication

More information
Python

Image Classification

Image recognition implementation with Keras. A CNN is built and trained with the CIFAR-10 dataset. Two models are trained: one without data-augmentation (77.25% accuracy) and the other with data-augmentation (78.04% accuracy).

More information
R

How fast can humans run?

An implementation of "A Simple Random Walk Model for Predicting Track and Field World Records"

A prediction model is built for the men's 100m world record, and human performance limits are estimated using Monte Carlo simulations.

More information
Original paper
Presentation
R

EUR/CHF forecast

The goal of this study is to fit an ARIMA model to forecast the EUR/CHF currency exchange rate. Different models are obtained through two trend removal methods: a linear model, and differencing.

More information
Report
R

Analyzing schizophrenia

A Generalized Linear Mixed Model (GLMM) is fitted in order to study the correlated observations in longitudinal data of patients suffering from schizophrenia. The model parameter estimates reveal that ’male’ patients evolve less favorably than ’female’ patients, while age does not have a significant effect on the evolution of prevalence of thought disorders.

More information
Report
R

Credit applicant classification

The goal of this study is to determine, in an automated manner, whether new applicants present good or bad credit risk. 9 different machine learning models are trained to classify applicants based on their credit rating.

More information
Presentation
Report
Unity, Python

AI vs. Humanity

A collection of games where agents are trained with Reinforcement Learning.

More information
R, MATLAB, SQL, Wolfram Mathematica, Tableau, Excel, etc.

Other projects

Small projects that I work on during my free time.

More information

Education & Experience

  1. Statistician / Data Scientist

    Diabetes Center Berne (DCB)


    • Contribute to the development of a continuous glucose monitoring (CGM) sensor performing data analysis and modeling of in-vitro glucose measurements.
    • Support internal and external clinical studies with design suggestions, protocol and statistical analysis plan (SAP) writing, sample size estimations, and analyses.
    • Optimize manually performed processes by implementing automatic data processing pipelines and algorithms in R for collaborators and coworkers.

  2. M.Sc. in Statistics

    Université de Neuchâtel (UniNe)

    Grade: Summa Cum Laude 5.85/6.00

    Relevant coursework: computational statistics, data mining, generalized linear models, statistical learning, time series analysis, multivariate analysis.
  3. Machine Learning Engineer

    CHEQUE - Der intelligente Cloudspeicher


    • Researched state-of-the-art machine learning implementations in Python, in addition to performing data wrangling and feature engineering to develop a document management mobile application.
    • Employed transfer and ensemble learning in object detection models trained on self-annotated images for multidomain document layout analysis.
    • Achieved above 97% accuracy in text classification by applying text mining and NLP techniques to unstructured data in English and German.
    • Held 2-4 meetings per week with the founder to analyze business cases and brainstorm technical solutions to customer needs.

  4. B.Sc. in Physics / Erasmus+

    Universität Zürich (UZH)

  5. B.Sc. in Physics

    Universidad de Cantabria (UC)

Further Training

  1. Advanced Clinical Trial Designs

    Swiss Epidemiology Winter School 2023

Main Skills

Python

R

MATLAB

Git

Languages

Spanish

Native

Basque

Native

English

Native proficiency: CPE Cambridge C2

French

Intermediate: EOIDNA B1

Contact

© 2023 Aritz Lizoain