Manuel Arias
Data Scientist | Data Analyst | Data Engineering Enthusiast
Transforming data into actionable insights through Analytics, Data Engineering and Machine Learning.
Python
R
SQL
Databricks
Power BI
TensorFlow
scikit-learn
Pandas
NumPy
Azure
Azure AI
Snowflake
OpenAI
Gemini
SQLite
Jupyter
Git
GitHub
VS Code
NotionPythonRSQLDatabricksPower BITensorFlowscikit-learnPandasNumPyAzureAzure AISnowflakeOpenAIGeminiSQLiteJupyterGitGitHubVS CodeNotionBuilding decisions on top of real, operational data.
I'm a Data & AI professional based in Santo Domingo, currently working at Fresenius Kabi Medical, where I transform real-time operational data into KPIs, automated workflows, and insights that support better business decisions. My day-to-day combines Python, SQL, Databricks, and data quality monitoring to solve real operational challenges and turn raw data into actionable insights.
Alongside my professional experience, I'm pursuing a degree in Computer Science Engineering while expanding my expertise in Data Engineering, Machine Learning, and cloud technologies. I'm passionate about building practical solutions that bridge business needs with modern data technologies and create measurable impact.
Where I'm currently building.
Data & Automation Technician
- Analyze real-time operational data from industrial systems and automated sensors.
- Develop KPIs and performance metrics that drive operational decisions.
- Automate data workflows in Python and reduce manual reporting overhead.
- Monitor data quality and integrity across multiple ingestion sources.
- Perform data cleaning, transformation and modeling for analytics consumption.
- Identify operational inefficiencies through exploratory analytics.
- Support decision-making through reporting, dashboards and insights.
- Collaborate cross-functionally with operations and engineering teams.
Case studies across the data lifecycle.
From ETL pipelines to executive dashboards and predictive models — selected projects that show how I move from raw data to business outcomes.
Inventory Segmentation & Profit Optimization
Profitability across an inventory of 54,000+ SKUs was opaque, making it hard to focus optimization efforts.
Built an end-to-end Databricks pipeline that cleaned, enriched and segmented products by margin and rotation, exposing the categories driving profit.
- 54K+ records processed
- Segmentation surfaced top-margin clusters
- Recommendations focused optimization scope
DatabricksPythonSQLPySpark
Data Engineering & Analytics Pipeline
Disparate raw sources required manual wrangling before any analysis could begin.
Designed a Python + SQLite pipeline covering ingestion, cleaning, transformation, analytical queries and automated reporting.
- Reproducible ETL stages
- Clean analytical layer in SQL
- Automated reporting outputs
PythonSQLSQLite
Business Intelligence Dashboard
Stakeholders lacked a single view of sales performance and key business indicators.
Modeled the dataset and built interactive Power BI dashboards focused on KPI tracking and executive narrative.
- Interactive executive view
- Sales KPIs at a glance
- Drill-downs by dimension
Power BIDAXData Modeling
Machine Learning & Predictive Analysis
A business question required a quantitative prediction beyond what descriptive analytics could offer.
Trained classification models in Python and R, evaluated performance and tuned hyperparameters with a business-impact lens.
- Multiple model comparison
- Tuned hyperparameters
- Business-aligned evaluation
PythonRscikit-learnTurning operational data into business clarity.
A glimpse of the kind of dashboards and analyses I build — KPIs, trends and segmentations that drive decisions.
Operational Throughput — Last 12 Months
Margin Contribution by Segment
Pipeline Latency Reduction
The tools I ship with.
A curated stack covering programming, data engineering, databases, analytics and visualization.
A stack built for the full data lifecycle.
Programming
PythonRSQLC#C++Data Engineering
Data ModelingDatabricksData QualityAutomationMachine Learning
scikit-learnTensorFlowEDAModel EvaluationHyperparameter TuningArtificial Intelligence
TensorFlowGeminiAzure AIOpenAI APICloud
AzureSnowflakeDatabricksDatabases
SQLSQL ServerSQLiteQuery OptimizationRelational DBsVisualization
Power BIMatplotlibggplot2Data StorytellingTools
GitGitHubJupyterVS CodeNotionPyCharmExcelGoogle ColabCode, commits and craft on GitHub.
Active repositories, ongoing learning and project work — all version-controlled and public.
Contribution Activity
last 12 monthsFoundations and continuous learning.
University Education
Computer Science Engineering
Bachelor's degree at PUCMM — foundations in algorithms, software engineering, databases and applied mathematics.
Professional Certifications
Data Analyst
Hands-on certification at CENFOTEC covering analytics workflows, SQL, dashboards and business reporting.
.NET Programming
Programming certification at CENTU focused on C# and the .NET ecosystem.
Information Technology
Technical certification at CENTU covering IT fundamentals, systems and infrastructure.
Notes on data, engineering and craft.
Soon: long-form notes on SQL, Python, data engineering, Power BI, machine learning and growing a career in data.
SQL
Python
Data Engineering
Power BI
Machine Learning
Career
Let's build something with data.
Open to Data Analyst, BI Analyst, Junior Data Engineer and Junior Data Scientist opportunities — locally and internationally.