We build data infrastructure that drives decisions.
We are The Big Data Company. A close-knit team that loves a good puzzle. You won't hear us chasing the latest AI trends; honestly, all those empty buzzwords make us a bit twitchy. We'd rather be building systems that work and deliver on what they promise.
IRIS is a location strategy platform, built for retail networks and franchise operators across 25+ markets.
A forecast is not a decision. IRIS helps you make better decisions.
A failed opening is wasted money. Our algorithms help you learn from the past so you can make better decisions in the future. We don't just give you a forecast, we back it up. We are transparent about the uncertainty margins and the variables driving the prediction.
1 Validated out-of-sample against 2020-2025 opening cohorts.
Visit irisplatform.nl →Whether we're anonymizing millions of documents for municipalities or designing spatial algorithms to understand retail networks, we don't stop until the infrastructure is rock solid. No off-the-shelf solutions. We deliver custom engineering for complex data.
Evaluating and comparing international expansion sites without relying on local, fragmented, and disconnected data models.
Reducing reliance on manual, error-prone field data collection for large-scale geographic property assessments.
Automating the ingestion, cleaning, and structuring of millions of raw geographical coordinates into production-ready predictive models.
not quarters Direct to production
- Privacy-first infrastructure Anonymising millions of government records at scale, fully GDPR-compliant.
- Retail risk modeling A single risk score for every commercial property in the Netherlands.
- Real-time footfall fusion Combining smartphone pings with IR camera data for live footfall intelligence.
- Market clustering Identifying operational similarity between companies beyond static sector codes.
We deliver robust solutions without the hassle. We sell the IRIS platform on a subscription model. If your challenges are highly specific, we don't force a standard solution; our team builds custom software.
Absolutely not. We skip the month-long discovery phases that end up as slide decks full of AI hype and little concrete output. We focus strictly on applied data science: spatial modeling, predictive analytics, and solid engineering. If your data is messy and you don't actually need machine learning yet, we'll say so.
You work directly with the technical team behind the solution. That makes us fast and flexible.
Our work is heavily anchored in Python, utilizing libraries like GeoPandas, Shapely, and PySpark, backed by highly scalable infrastructure like Google BigQuery and custom GIS backends. We build for performance, security, and permanence.
Because we are a small, focused team, we move fast. We typically ship initial data prototypes, route-scoring runs, or pipeline integrations within the first few weeks of kicking off a project.
More often than you think. We will explicitly tell you when the model is uncertain, when the historical training data is too thin to trust, and when your local, on-the-ground knowledge should outweigh our forecast.
We validate out-of-sample and track retrospective accuracy over time. We have been wrong before. When we are, we document it, adjust the pipeline, and show you the math.
Yep! All the more reason to carefully determine which connections you can actually trust. Chance correlations that collapse the moment the economy shifts aren't worth building predictions on.
We could have hired an expensive agency to create abstract, corporate 3D art, but at our core, we're just engineers who prefer staring at terminals. Since the actual code for proprietary infrastructure like IRIS and Blink is strictly confidential, please enjoy this ASCII art instead.
Sounds like something for you?
Drop us a line.
info@thebigdatacompany.nl →The Big Data Company B.V.
Princetonlaan 6 · 3584 CB Utrecht, Netherlands
+31 30 899 9477