Skip to content
View GaiskaSalomon's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report GaiskaSalomon

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. Markdown is supported. 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
GaiskaSalomon/README.md
Gaiska Salomon - Data Scientist | Machine Learning | Time Series & Forecasting | Statistical Modeling

LinkedIn Mexico English


About

Data Scientist and Ph.D. Candidate in Statistics & Data Science with experience in statistical modeling, machine learning, time-series forecasting, quantitative research, software development, and applied AI.

I build reproducible analytical workflows from data preparation and feature engineering to modeling, validation, evaluation, and technical delivery.


Selected Work

Production-stable Python package for non-stationary extreme-value inference.

Python · Statistical Inference · Monte Carlo · Extreme Value Theory

Climate-informed commodity forecasting with walk-forward validation, Bayesian modeling, and cost-aware backtesting.

XGBoost · LightGBM · PyMC · Time Series

Spanish domain LLM pipeline with QLoRA fine-tuning and RAG on PostgreSQL + pgvector.

PyTorch · Hugging Face · QLoRA · RAG


Stack

Python SQL R scikit-learn XGBoost PyTorch PostgreSQL Docker


Open to Opportunities

Data Science · Research Data Science · Applied Scientist · Machine Learning · Statistical Modeling · Time Series & Forecasting

LinkedIn

Pinned Loading

  1. nsevt nsevt Public

    Calibrated GPD tail inference in Python: continuous and grouped fits, profile intervals, permutation trends, Monte Carlo calibration, and multi-source robustness.

    Python 1

  2. climate-commodity-alpha-lab climate-commodity-alpha-lab Public

    Quantitative research: do weather & climate-risk features improve commodity return forecasts? Walk-forward validation, XGBoost/LightGBM, cost-aware backtesting.

    Jupyter Notebook 1

  3. agrollm-es agrollm-es Public

    Spanish domain LLM pipeline: custom dataset → QLoRA fine-tuning (Qwen2.5) → RAG on PostgreSQL/pgvector → evaluation. Runs locally on a single GPU.

    Python 1