Featured project
Bank customer churn analysis
Where churn risk concentrates and what explains it
Identify which customer profiles concentrate churn at a bank with customers in Germany, Spain and France.
- Looker Studio
Hi, I’m
Data Analyst · Data Science
Turning data into decisions: dashboards with a story, models evaluated honestly.
Alpha Vantage APIAzure Data Lake Storage Gen2CSSConfluent Cloud (Kafka)DatabricksDatabricks (Delta)Diagramas (draw.io, Excalidraw)Google ColabGoogle Maps PlatformHTMLHugging Face TransformersJavaScriptKerasLooker StudioMLflowNumPyOSRMPower BIPySparkPyTorchPythonRRStudioSQLSchema RegistrySciPySpark MLTensorFlowTensorFlow / KerasVercelapyoricorrplotggthemesjanitorkagglehublubridatematplotlibmicemlxtendmodelsummarypandasplotlypytestreadxlscikit-learnseabornskimrstatsmodelstidyversetidyverse (dplyr, ggplot2)
01.
Featured projects
Featured project
Employee attrition risk factors
Insight dashboard + decision tree to prioritise retention
Understand which factors (education, distance to office, salary, satisfaction, gender, department) are associated with employee resignation and propose retention actions.
- Python
- pandas
- scikit-learn
- Databricks
- Looker Studio
Featured project
Executive sales summary — RetailCo
Year-over-year growth by segment, category and region with a year selector
Give management an executive view of sales growth versus the previous year.
- Looker Studio
Featured project
Productivity overview — GarmentPro Industries
Actual vs target productivity by department, team and quarter, designed for visual attention
Compare actual vs target productivity and find which operational variables (overtime, idle time, style changes, incentives) are associated with lower performance.
- Looker Studio
Featured project
Global bike sales 2013–2023 on Databricks
End-to-end capstone: PySpark exploration, business hypotheses and regression
Run a full data science project («50 steps») on bike sales: frame business hypotheses, prepare the data and predict quantity per order (Order_Quantity).
- Databricks
- PySpark
- Spark ML
- Python
- scikit-learn
Featured project
Predicting on-time delivery in e-commerce
Random Forest, logistic regression and K-Means to anticipate delays
Classify whether an order arrives on time and find which factors and segments concentrate delays.
- Python
- pandas
- scikit-learn
- matplotlib
- seaborn
- Databricks
Featured project
Pneumonia classification on chest X-rays
From a dense network to MobileNetV2 transfer learning and GAN-generated data, with a single held-out test evaluation
Classify X-rays as normal or pneumonia, comparing the course's techniques in a controlled way.
- Python
- TensorFlow / Keras
- scikit-learn
- Databricks
- kagglehub
Featured project
Medical specialty classification: LSTM vs Bio_ClinicalBERT
NLP on medical transcriptions with a custom BiLSTM and a pre-trained clinical transformer
Predict which specialty (10 classes) a medical transcription belongs to.
- Python
- TensorFlow / Keras
- Hugging Face Transformers
- PyTorch
- scikit-learn
- Databricks
Featured project
Time series with LSTM: energy and stocks
Forecasting electricity demand and stock prices, compared against honest baselines
Test LSTM and GRU on real time series and measure whether they beat simple baselines.
- Python
- TensorFlow / Keras
- scikit-learn
- pandas
- Alpha Vantage API
- Databricks
Featured project
ACME EV — real-time telemetry for an electric-vehicle fleet
Kafka (Confluent) with Schema Registry and DLQ, a live dashboard on Vercel and a Gold layer in Databricks
Ingest and exploit telemetry from a fleet of up to 10,000 electric vehicles across 10 Latin American branches (GPS every 30 s and status every 60 s), guaranteeing availability, integrity and confidentiality, with 20% annual growth.
- Python
- Confluent Cloud (Kafka)
- Schema Registry
- Databricks (Delta)
- Vercel
- JavaScript
- Google Maps Platform
- OSRM
- pytest
Featured project
Telecom X — customer churn analysis
ETL + EDA in Colab with a written final report: where and why customers leave
Clean the Telecom X data (7,267 customers) and explain which profiles and conditions concentrate churn, with recommendations to reduce it.
- Python
- pandas
- NumPy
- matplotlib
- seaborn
- Google Colab
02.
More projects
Dashboards & storytellingSales behaviour — Adventure WorksLooker StudioDeep LearningAbnormal ECG detection with RNN and LSTMPython · TensorFlow / Keras · SciPyDeep LearningIMDb sentiment analysis with LSTMPython · TensorFlow / Keras · DatabricksLabsDeep Learning labsPython · PyTorch · TensorFlow / KerasLabsMachine Learning labsPython · pandas · scikit-learnData engineeringConfluent events → bronze layer ingestion (setup)Databricks · Confluent Cloud (Kafka) · Azure Data Lake Storage Gen2ProgrammingProgramming logic in JavaScript (Alura)JavaScript · HTML · CSSProgrammingR fundamentals with Guatemalan dataR · RStudio · tidyverse (dplyr, ggplot2)LabsStatistics labs in RR · tidyverse · lubridateLabsProgramming for Data Science labs (Python and SQL)Python · pandas · NumPyData engineeringData architecture business casesDiagramas (draw.io, Excalidraw)
Some professional projects are not shown here due to data confidentiality.
03.
About me
Accountant/Auditor and Data Analyst with an accounting background. Specialised in extracting, validating and strategically reporting key data (sales, inventory, payroll/ISR). Advanced Excel, SQL, Python, Power BI, Looker Studio and Databricks for process automation and business intelligence. Continuing education in Data Science and IT Management.
Education
- Specialisation in Data Science and Master in IT ManagementUniversidad Rafael Landívar2026 – 2027 (in progress)
- Master in Financial AdministrationUniversidad de San Carlos de Guatemala (USAC)2023 – 2024 (not completed)
- Public Accounting and AuditingUniversidad San Carlos de Guatemala2018 – 2023
Certifications
- Microsoft Certified: Power Platform Fundamentals (PL-900)
- Databricks Fundamentals Accreditation
- Lean Six Sigma Yellow Belt Certified
04.
Contact
Looking for an analyst who understands the business and backs it up with data? Email me or check my work on GitHub.