Skip to content
View ayorick23's full-sized avatar
:octocat:
:octocat:

Block or report ayorick23

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
ayorick23/README.md

Dereck Mendez — Data Analyst · Business Intelligence

Turning business questions into reliable data, clear dashboards and reproducible analysis.

Portfolio LinkedIn Email Kaggle

✦ About

I'm an Engineering Consultant at ACF Technologies (LATAM), working on data and machine learning solutions for workforce management in banking and telecom:

  • Demand forecasting - maintaining and improving predictive models that forecast contact-center demand and handle time, the input for automated staffing decisions.
  • Workforce scheduling - a resource-allocation project that turns demand forecasts into agent schedules aligned with expected volume.
  • Data platform - building the team's own data warehouse on a medallion architecture (bronze → silver → gold) to centralize and standardize operational data.

Before that, I spent three years in People Analytics, automating HR reporting with Python and building Power BI and Looker Studio dashboards for teams across Guatemala, Costa Rica and El Salvador.

✦ Currently

building:  ecommerce-medallion-pipeline  →  Gold layer (star schema) with dbt + DuckDB
learning:  dimensional modeling · orchestration with Airflow
open_to:   Data Analyst · Business Intelligence roles

✦ Featured Projects

Complete

Global salary benchmark for data & AI roles with hypothesis testing, bootstrap confidence intervals and purchasing-power adjustment. Contract-tested ETL, business SQL and an interactive Power BI dashboard.

Python · SciPy · Pandera · SQL · Power BI
Complete

End-to-end churn prediction system: model selection, experiment tracking, drift detection, champion/challenger retraining and an explainable API + dashboard deployed on Hugging Face Spaces.

LightGBM · MLflow · DVC · Evidently · FastAPI · Docker
In progress

Incremental batch pipeline replaying ~100k real orders day by day through Bronze → Silver → Gold, with row-level lineage, idempotent reprocessing and fail-fast data quality gates.

Polars · Pandera · dbt · DuckDB · Airflow

✦ Explore the full case studies on my portfolio →

✦ Tech Stack

DATA & ANALYTICS
Python SQL Pandas Polars NumPy SciPy

BI & VISUALIZATION
Power BI Looker Studio Excel Streamlit

DATA ENGINEERING
SQL Server PostgreSQL DuckDB dbt Airflow

MACHINE LEARNING & MLOPS
scikit-learn LightGBM MLflow DVC FastAPI

ENGINEERING PRACTICES
Git GitHub Actions Docker pytest

Pinned Loading

  1. data-ai-compensation-benchmark data-ai-compensation-benchmark Public

    A data-driven analysis of global compensation trends across Data and AI roles, experience levels, and countries, uncovering market patterns and career opportunities.

    Python 1

  2. telco-churn-mlops telco-churn-mlops Public

    End-to-end Machine Learning & MLOps platform for telecom customer churn prediction, explainability, model serving, monitoring and retention intelligence.

    Python 1

  3. ecommerce-medallion-pipeline ecommerce-medallion-pipeline Public

    Incremental batch data pipeline for e-commerce order data, built with Airflow and Polars using a medallion (bronze/silver/gold) architecture, Pandera data quality gates, and dimensional modeling on…

    Python 1

  4. ayorick23.github.io ayorick23.github.io Public

    Professional portfolio showcasing projects and experience in Data Science, Machine Learning, BI, and MLOps.

    TypeScript