Skip to content
View elsakeleko's full-sized avatar
📊
Data Science @ WHS | RAG, causal inference, forecasting | open to Data Science /
📊
Data Science @ WHS | RAG, causal inference, forecasting | open to Data Science /
  • Gelsenkirchen, Germany

Block or report elsakeleko

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
elsakeleko/README.md

Hi, I'm Elsa 👋

Data Scientist · Machine Learning & Data Engineering — based in Gelsenkirchen, Germany. B.Sc. Data Science student at Westfälische Hochschule. Languages: French (native), German (C1), English.

I build, validate and ship ML solutions for real business problems: from messy data to a deployed model.

What I work with

Area Tools
Languages Python, R, SQL, C, C++
ML & AI scikit-learn, TensorFlow, NLP, time series, causal inference, survival analysis
LLM & RAG Ollama, LangChain, ChromaDB, OpenAI / Azure OpenAI, FastAPI
Data engineering ETL, data migration, data quality, Spark, Databricks, BigQuery
BI Power BI, Tableau, Looker Studio
DevOps Docker, Git/GitLab, CI/CD, n8n, AWS / Azure / GCP

Selected work

  • Local RAG advisory system (team project): Ollama + ChromaDB + FastAPI, containerised with Docker, with systematic answer-quality evaluation and source citations.
  • Causal inference for clinical trials (national data science competition, R): identifying patient subgroups with heterogeneous treatment effects using BART, Virtual Twins and Causal Forest.
  • Time series forecasting: trend and seasonality analysis and demand forecasting models.
  • ML on 3D body-scan data (internship): data quality, feature engineering and model validation against baselines.

Currently

  • Building and evaluating RAG pipelines
  • Contributing to open-source time-series and causal-inference libraries

Contact

LinkedIn · elsakeleko5@gmail.com

Timeline

Career and project timeline with durations: TIMELINE.md

Popular repositories Loading

  1. elsakeleko elsakeleko Public

    Profile README

  2. darts darts Public

    Forked from unit8co/darts

    A python library for user-friendly forecasting and anomaly detection on time series.

    Python

  3. dowhy dowhy Public

    Forked from py-why/dowhy

    DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

    Python

  4. chroma chroma Public

    Forked from chroma-core/chroma

    Search infrastructure for AI

    Rust

  5. co2-forecasting co2-forecasting Public

    Forecasting monthly CO2: seasonal naive vs Holt-Winters vs SARIMA vs gradient boosting, rolling-origin CV

    Python