Hire the Best Data Analysts
in Spain

I help businesses turn raw, unstructured data into clean, reliable insights they can actually use. As a Data Analyst with strong Data Engineering experience, I work across the full data lifecycle from data extraction and transformation to analysis, visualization, and reporting. This means you don’t need multiple freelancers to handle your data. What I do best: Data cleaning, preprocessing, and analysis (Python, Pandas) SQL querying, database analysis, and optimization ETL pipelines and data integration from APIs, files, and databases Dashboard creation and reporting (Power BI / Tableau / Excel) Automating data workflows and recurring reports Tools & Technologies: Python (Pandas, NumPy, Scikit-learn) SQL (PostgreSQL, MySQL, SQL Server) Power BI / Tableau / Excel ETL pipelines, APIs, data modeling I focus on accuracy, performance, and clear communication. Whether you need clean data, automated pipelines, or decision-ready dashboards, I deliver solutions that are reliable and easy to maintain.

Quantitative researcher and data scientist with 15+ years of experience with data management and analysis and applying machine learning, econometrics, and geospatial analytics to high-impact development problems. Proven track record designing end-to-end data pipelines, building predictive models, and delivering actionable insights for international organisations (World Bank, IADB) and academic research. Skilled in R, Python, SQL, and cloud-based GIS tools; experienced translating complex analyses into dashboards and policy-relevant products for non-technical audiences. Technical Skills Programming & Analytics: R (tidyverse, sf, Shiny, package development), Python (pandas, scikit-learn, GeoPandas, web scrapping), Stata, MATLAB, SQL, LaTeX, Artifical Intelligence Data Visualisation & BI: R Shiny, Power BI (with ArcGIS integration), Tableau, Flurish,Python Machine Learning & Econometrics: Supervised/unsupervised ML, spatial econometrics, causal inference (RCT, DiD, RDD, IV), time-series, regression modelling GIS & Remote Sensing: ArcGIS Pro, QGIS, Google Earth Engine, ENVI; raster & vector data processing at scale Languages: Spanish (native), English & Portuguese (fluent), Catalan (intermediate), Italian (basic)

Your dashboard is not the problem. The problem is the spreadsheet behind it. The export nobody fully trusts. The KPI definition that changed three times. The manual step someone forgot to document. The number that looks right until another report says something different. That is the part I fix. I work on broken dashboards and fragile reporting workflows: CRM exports, spreadsheets, CSV files, APIs, R Shiny apps, and internal reports that technically exist, but are too manual, inconsistent, or unclear to rely on. I do not just make dashboards look better. I review how the data is created, where the reporting logic breaks, which fields are safe to use, what needs to be cleaned or restructured, and what should be documented so the same problem does not come back next week or next month. You will not get a passive data cleaner. You will get someone who asks practical questions, challenges unclear logic, makes decisions when the structure is messy, and keeps the work moving instead of waiting for perfect instructions. What I can do for you: • Fix broken dashboards where the numbers do not match the source data • Audit R Shiny apps and reporting workflows for logic, structure, and data issues • Rebuild manual reporting processes built around repeated Excel, CSV, CRM, or API exports • Clean and structure messy operational data before it reaches a dashboard • Review KPI definitions and reporting logic • Build R/Shiny dashboards for internal decision-making • Create R Markdown / Quarto reports that can be updated again • Add validation checks before numbers reach the final report • Document the workflow so your team can maintain it later Recent outcomes: • Reduced manual reporting time by ~80% by replacing repetitive CRM exports with an API-connected R/Shiny dashboard • Reviewed operational, clinical, and billing data in a multi-location healthcare CRM environment • Structured fragmented transaction records into a clearer reporting workflow • Turned raw survey data into validated customer segments for strategic targeting Core tools: R, SQL, Shiny, R Markdown/Quarto, tidyverse, Excel/CSV workflows. You are probably a good fit if you already have reports, dashboards, spreadsheets, apps, or exports — but the process is too manual, inconsistent, unclear, or hard to trust.

Top Rated Data Analyst with 6+ years of experience using Python, SQL, R, Power BI, and machine learning to clean complex data, build predictive models and forecasts, automate reporting, and turn results into clear business decisions. Across 55 Upwork contracts, I have supported businesses, finance professionals, and research teams with projects ranging from large-scale data processing and customer analytics to financial forecasting, statistical modeling, and biomedical research. I can help you with: • Data extraction, cleaning, merging, matching, deduplication, and validation • Exploratory data analysis and identification of meaningful patterns • SQL querying, database analysis, and recurring reporting workflows • Large-scale data processing with Python, pandas, SQL, and DuckDB • Machine learning classification, regression, gradient boosting, random forests, clustering, and feature engineering • Predictive analytics, model comparison, cross-validation, probability calibration, leakage detection, and error analysis • Time-series forecasting, backtesting, financial modeling, pricing, demand, profitability, and risk analysis • Customer segmentation, retention, churn, cohort analysis, and ROI modeling • Power BI dashboards, Excel reports, KPI tracking, and data visualization • Statistical analysis using R, Stata, SPSS, and Python • A/B testing, hypothesis testing, causal impact analysis, and experimental design • NLP, text classification, thematic analysis, and human-verified AI-assisted workflows Selected project experience includes: • Built a Python and DuckDB workflow to process 483.9 million records and create a validated 395.9 million-record analytical sample • Analyzed 2.3 million transactions to measure pricing and behavioral responses • Developed credit-risk prediction models and evaluated 84 insolvency-model specifications • Built customer-segmentation, pricing, demand, margin, and forecasting workflows using Python and SQL • Conducted reproducible biomedical and proteomics analysis in R across 146 samples and approximately 5,300 protein groups • Combined and validated economic, financial, and policy data from multiple international sources • Produced dashboards, forecasts, statistical reports, and decision-ready recommendations for business and research clients My primary tools include Python, pandas, NumPy, scikit-learn, SQL, DuckDB, R, Stata, Excel, Power BI, SPSS, MATLAB, and LaTeX. I use AI to accelerate appropriate parts of analysis, coding, documentation, and quality assurance—but I independently verify the results. My workflows include reproducible code, control checks, documented assumptions, validation tests, and clear explanations of limitations. You will receive organized data, maintainable code, reliable analysis, professional visualizations, and a concise explanation of what the findings mean for your project. Send me your data and objectives, and I’ll suggest a practical approach.

Need to collect, organize, and deliver reliable data? I build production-ready backend systems that automate the entire data lifecycle—from data collection and validation to PostgreSQL databases, ETL pipelines, APIs, and workflow automation. Instead of delivering isolated scripts, I design complete systems that are reliable, maintainable, and built to grow with your business. Whether you're creating an internal platform, integrating third-party APIs, or processing large volumes of data, my goal is to build infrastructure that continues delivering value long after deployment. My work focuses on three areas: Backend Engineering • FastAPI applications • REST APIs • Backend services • Internal tools Data Engineering • ETL pipelines • PostgreSQL databases • Data validation & processing • Data migration • Data architecture Automation & Data Collection • Workflow automation • API integrations • Custom web scraping • Browser automation • Large-scale data extraction Technology Python • FastAPI • PostgreSQL • SQLAlchemy • Docker • Playwright • BeautifulSoup • Selenium • Pandas • Git • Linux I believe good software isn't measured by how quickly it's written, but by how reliable it is six months later. That's why I focus on clean architecture, maintainable code, and solutions designed for long-term use. If you're looking for an engineer who can build reliable backend systems and data infrastructure—not just scripts—I'd be happy to discuss your project.

Most AI projects don't fail at the demo — they fail in production, when the RAG hallucinates or the agent breaks silently. I'm an AI engineer who builds the reliability layer: RAG systems, agents, and LLM backends that survive real users, not just a nice demo. WHO I WORK WITH Teams and founders who tried a chatbot that hallucinated, wired up automation that broke without warning, or know AI should save them time but don't know what to build first. WHAT I BUILD • Grounded RAG & audits — retrieval that cites its sources and says "I don't know" instead of inventing answers. I'm often brought in to fix pipelines returning wrong or unreliable results. • Multi-agent systems — agents that use tools, keep context, and hand off to humans, with approval gates, logging and cost control. • End-to-end AI apps — FastAPI backends (streaming, auth, structured outputs, containerized deploys) plus the React frontend to use them: dashboards, chat UIs, internal tools. WHY ME (the honest version) I review the architecture before writing a line of code. If AI isn't the right tool for your problem, I'll tell you. My work lives at the layer where projects actually fail — retrieval accuracy, agent reliability, evaluation. 90% Job Success across 10 jobs, with clients who come back for follow-on phases. RECENT WORK • RAG system audit & optimization (retrieval + evaluation) • Regulated-lab AI agent — human-in-the-loop + audit trail • Record matching & email enrichment — confidence-based routing Core stack: Python · FastAPI · LangChain/LangGraph · React (OpenAI / Claude). Certified: Machine Learning Specialization (Stanford / Andrew Ng), LangChain for LLM App Development (DeepLearning.AI), NVIDIA Generative AI. Send me one system or workflow that's stuck or eating your team's time. I'll reply with a short, honest teardown — what I'd build first, what I wouldn't, and what it'll take. No pitch.