Hire the Best Shiny Specialists
in Spain

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)

✅ Top 1% part of Upwork's EXPERT-VETTED program | NO AGENCY SOLO DEVELOPER 🎖️ 8 years+ of experience in Data Science 🏅 180+ Upwork Projects 💯 Less than 1 Hour Response time My specialty is to take your business problem and find a suitable end to end solution using AI and programming tools from Python, R, JavaScript programming languages. My extensive experience and wide skillset from data acquisition, model training to production grade application or REST API development will save you time and costs (material or psychological i.e. trying to find developers to make MVP, organize and support communication within team). AI Agentic systems are overtaking markets with potential impact on various businesses and creating opportunities to utilize. My skills in AI Agentic system development using Langchain, LangGraph, CrewAI, Autogen, RAG, MCP, Retell ai, Elevenlabs will give you opportunities to cut costs and optimize your business operations. My skills include machine learning, deep learning, computer vision, web scraping, data engineering, web development, and data visualizations. I can create interactive web applications and dashboards using Python's Dash framework and R's shiny package so you will be able to observe, analyze and present various aspects of your business and other activities in practical ways. My expertise also includes the development of graphical user interface GUIs with Python's Kivy framework. In Computer Vision, my skills include image classification, object detection, and image segmentation with Python tools such as Tensorflow, Keras, CNNs (LeNet, AlexNet, VGG1619, InceptionV3, ResNet50), SSD, YOLO, TFOD, and Mask R-CNN. Importantly, I have skills in math and statistics essential for understanding processes behind code and interpreting outcomes from it. I have done my MBA with a focus on data science. I have been working as an accountant for around five years, including a member of the Big Four and as Data Scientist in a local IT company focused on DS. Thus, I understand finance from theoretical and practical sides and can apply code to analyze vast amounts of financial or other data efficiently. Considering my previous experience, my domain knowledge in finance, marketing (CTR, CLV), process optimization, and other business areas, I will focus on understanding your business goals and implementing solutions to make them come true. My skills include: ✅ Data Science ✅ Machine Learning ✅ Deep Learning ✅ Algorithmic Trading ✅ Generative AI ( Langchain, IIamaIndex, LangGraph, LangSmith, HuggingFace, StableDiffusion, Midjourney, OPEN AI, CHAT GPT4, CHAT GPT3.5, Mistral7B, Gemini, Cursor, Ollama, CrewAI, AutoGen, MCP, Google MCP Toolbox for Databases) ✅ Prompt Engineering (ICO, TESSA, ReAct, Chain of Thought, Map Reduce, Refine) ✅ AI Agents, Inbound & Outbound & Batch Calls, Chatbots, RAG, Conversational Agents, VAPI, Retell.ai, Make com, gohighlevel, n8n, telnyx, twilio ✅ Full Stack Development (React, React Native, Next.js) for AI integration ✅ Interactive Visualizations/Dashboards ✅ Data Engineering (MySQL, MongoDB, PostgreSQL, BigQuery, Oracle, SQLServer, Pinecone, ETL) ✅ Python, R, SQL ✅ Object Oriented Programming (OOP) ✅ PEP-8 (pylint, isort, flake8, autopep, black, docstrings, pydocstyle, mkdocs) ✅ Web development (interactive dashboards Dash) ✅ Bot Development (Telegram) ✅ Graphical User Interfaces (GUI) Kivy ✅ Big Data (Spark) ✅ Recommender Systems ✅ DevOps (ML Deep Learning model deployment on cloud, TDD, AWS, GCP, Azure, Docker, REST API) ✅ OCR ✅ Computer Vision ✅ Audio Processing ✅ Natural Language Processing NLP (Bert, fastText, Langchain) ✅ CNN (LeNet, AlexNet, VGG1619, InceptionV3, ResNet50) ✅ Object Detection (R-CNN, SSD, YOLO, TFOD API) ✅ Image Segmentation (Mask R-CNN) ✅ Transfer Learning ✅ Time Series Analysis (ARIMA, SARIMA, LSTM, PROPHET) ✅ OpenCV ✅ Educational Tutorials ✅ Web Scraping ✅ Web Crawling ✅ API Clients ✅ Keras, Tensorflow, PyTorch ✅ Dash, Shiny, Plotly, Streamlit, React, Next.js ✅ Pandas, Numpy, Scipy, Scrapy, Selenium, requests, ggplot2 ✅ IOT (Raspberry Pi) ✅ REST API (Google Ads, Google Analytics, FB/META API, Stripe, CCXT, OPEAI etc.) ✅ REST API development (Flask, FastAPI)

I turn operational data spread across software platforms, spreadsheets, APIs, databases, and recurring exports into reporting systems your team can actually use. For a multi-location US healthcare group, I integrated data across more than 59,000 appointments, 54,000 patient records, and 19,000 procedures. I then built an API-connected R/Shiny reporting environment that reduced recurring manual reporting by approximately 80%. I am a strong fit when you need to: - Combine data from CRM/PMS platforms, REST APIs, databases, Excel, CSV, or JSON files - Replace repetitive spreadsheet reporting with a reusable workflow - Build an internal R/Shiny dashboard or analytical application - Investigate why reports, totals, or KPI calculations do not match - Clean and structure operational data before analysis - Add checks for missing, duplicated, or inconsistent records - Create reproducible R Markdown reports - Document the process so it can be reviewed and updated later My role is not limited to cleaning the file I receive. I investigate how the records are generated, ask practical questions early, clarify what each metric should include, and test unclear assumptions, transformations, and joins against the source data. When requirements or source structures are incomplete, I document the decisions and unresolved issues so the work can continue without hiding uncertainty. Selected project evidence: - Identified and documented schema conflicts, duplicates, and definition differences behind mismatched KPI figures across operational, clinical, and billing reports. - Turned changing bank-statement and financial-record formats into a structured R/Shiny review workflow with explicit matching rules, tolerances, and separate outputs for matched transactions and exceptions. - Converted raw survey and customer data into validated segments and practical recommendations for strategic targeting. - Created a custom D3.js/r2d3 patient-universe visualization across more than 54,000 records, allowing activity and follow-up patterns to be explored in a single interactive view. I work independently and communicate technical findings in language that non-technical stakeholders can use. Feedback from completed projects highlights my clear communication, commitment to quality, collaboration, and reliability. Core tools: R, Shiny, SQL, tidyverse, R Markdown, ggplot2, plotly, reactable, Leaflet, r2d3/D3.js, Excel, REST APIs, JSON/CSV, Git, and renv. If your data is already available but still requires too much manual work before it becomes useful, tell me what sources you have and what output you need. I can help define a clear first milestone and build from there.

I deliver end-to-end analytics, from messy multi-source data to clear decisions and measurable impact. I am an expert in R, Python, SAS, and Power BI; comfortable solving complex problems in data science, big data, forecasting, integration, and advanced analysis. My work blends statistical rigor with pragmatic engineering and clear storytelling so stakeholders understand the why and the what, and teams can operate solutions confidently after delivery. Data foundations matter; SQL, ELT, and ETL are the first step to bring disparate sources into clean structure and reliable governance. Once the data is in order, the real value begins: time series forecasting, predictive modeling, segmentation and classification, anomaly detection, and experiment-driven insights; all validated with robust procedures and monitored over time to keep performance stable. I surface results through intuitive Power BI experiences with effective data modeling, DAX, R or Python when needed, secure access, and narratives that make insights obvious and actionable. I also focus on adoption and communication. Beyond the analytics and dashboards, I produce professional tutorials and product videos with clear explanations, consistent visuals, and voiceover; helping clients train teams, shorten onboarding, and sell the value of their data products more effectively. The goal is not just a model or a report; the goal is usage, outcomes, and repeatable decision making. I am young, highly motivated, and I learn every day. Outside client work I am developing a blockchain and AI project; I stay hands-on with modern tools and practices; I am proactive by default and I enjoy hard problems. Continuous study and experimentation ensure every engagement benefits from current, battle-tested techniques. For my main client, b2b-aero, I am the sole data scientist and I lead all business intelligence, data, and statistics initiatives. I own architecture and modeling; I design forecasting and advanced analytics; I build and evolve dashboards; I establish data quality processes; and I translate business goals into production-ready solutions. The role requires autonomy, clear communication, and the ability to partner with leadership to turn ideas into outcomes. This skill set is industry-agnostic and applies to supply chain, finance, retail, manufacturing, healthcare, marketing analytics, and more. Whether the need is a forecasting system to reduce stockouts; a propensity model to improve conversion; a unified data mart to align teams; an automated data capture pipeline to enrich internal sources; or an executive KPI dashboard with drill-downs and narrative summaries; the approach is consistent: rigorous methods, pragmatic engineering, and design that makes insights simple to use. Engagements range from rapid audits to fixed-scope builds and ongoing partnerships. Communication is proactive; timelines are realistic; success is measured by business results: faster decisions, automated processes, lower costs, and better visibility. If you want a partner who connects statistics with real products, combining R, Python, SAS, SQL, and Power BI into secure, scalable, and visually compelling solutions, let’s talk.

I'm an economist, data scientist, and university professor with experience across clinical research, business development, and education. For me, data science isn't just about crunching numbers — it's about turning data into insights that solve real business problems or drive meaningful outcomes for organizations. My background includes building predictive models, and executing advanced machine learning projects using Python and R. I've led teams, created sales forecasts and competitive analysis frameworks using BI tools, and delivered technical presentations to stakeholders across European and US markets. More recently, I've been also working as a freelance biostatistician for a CRO, supporting clinical research projects with statistical analysis and study design.