DataModelLab beta
No code  ·  No setup  ·  60-second results

Your data has answers.
Get them in 60 seconds.

Upload any spreadsheet. Pick what you want to predict. Get a trained model, feature importance charts, and plain-English explanations — instantly.

Results in under a minute Tests 10+ ML algorithms automatically AI explains every result in plain English
No account needed  ·  Data processed in memory, never stored
datamodellab.com
Navigate
01Get Data
02Review Data
03Build Model
04Visualise
05Predict
Your path · Step 3/5
Build a model
Pick a target column and run.
Accuracy
94.2%
Excellent
F1 Score
0.93
macro avg
Best model
XGBoost
auto-selected
What drives the prediction feature importance
gdp_per_capita
0.88
life_expectancy
0.71
urbanisation
0.52
education_idx
0.37
60s
From upload to insight
Upload your CSV, pick a target column, and get your first trained model in under a minute. No waiting, no configuration, no code.
10+
Algorithms tested automatically
The engine runs XGBoost, Random Forest, Logistic Regression and more in parallel — returning the best model for your specific data automatically.
0
Lines of code required
Built for analysts, researchers, and domain experts. If you can use a spreadsheet, you can build and deploy a machine learning model here.
How it works
From spreadsheet to
trained model in 4 steps

No Python, no cloud setup, no data engineering. Just your data and the question you want answered.

01
Upload your data
Drop in a CSV or Excel file, or pull live data from 60+ public APIs — weather, finance, demographics, sports — with one click. No API keys needed.
02
Review and clean
See a full data preview, spot missing values and outliers, and exclude irrelevant columns. Ask the AI what to fix — it reads your actual data and tells you exactly what to do.
03
Build the model
Pick the column you want to predict. The engine tests every major algorithm, returns the best one, and shows you exactly which features drive the outcome — and by how much.
04
Predict and explore
Dial input sliders to make live predictions. Upload a batch CSV to score thousands of rows at once. Explore charts to find patterns you'd never spot in a spreadsheet.
Features
Everything you need,
nothing you don't
AI assistant built in
Ask questions in plain English. The AI reads your dataset, explains results, suggests what to fix, and finds data sources — all without leaving the app.
AutoML engine
Tests XGBoost, Random Forest, Logistic Regression, and more. Returns the best model automatically — no tuning, no expertise required.
Interactive charts
Scatter, histogram, box plots, heatmaps. Pin up to 4 charts side-by-side. Export to PNG or PDF.
Live predictions
Dial input sliders for instant single predictions. Or upload a CSV for batch scoring with confidence intervals on every row.
60+ live data sources
Pull from public APIs — weather, finance, crypto, demographics, sports — or search across 15 open data repositories. No keys needed.
Your data stays yours
All processing happens in memory. Nothing is written to disk or stored on our servers. Closing your tab clears everything completely.
FAQ
Common questions
Do I need to know how to code?
No. DataModelLab is built for analysts, researchers, and domain experts. Everything is point-and-click — no Python, no notebooks, no setup.
What file formats are supported?
CSV and Excel (.xlsx, .xls). Files are read directly in your browser session. Max file size is 50 MB.
Is my data stored on your servers?
No. Your data is processed in memory during your session and never written to disk or stored on our servers. Closing the tab clears everything.
Do I need an account?
You can run up to 3 analyses without signing up. Create a free account to save models and datasets, or upgrade to Pro for longer runs.
What kinds of problems can it solve?
Binary classification (yes/no outcomes), multi-class classification (3+ categories), and regression (predicting numeric values). The engine detects which type fits automatically.
How accurate are the results?
It depends on your data. The Quick run (1 min) gives a strong baseline. Longer runs (up to 30 min) do hyperparameter search and often improve results meaningfully.
Try it now.
Takes about 60 seconds.

Upload a CSV, pick a target column, and get your first model. No account needed.

DataModelLab

beta
Step 1 of 5 Get your data
Choose one of the three options below to load a dataset, then move to Review Data.
Browse datasets
Saved · samples · public repos
Pick from your saved datasets, classic ML sample datasets (Titanic, housing prices), or download CSVs from Kaggle, UCI, and more.
Find data with AI
60+ live APIs · 15 repositories
Describe what you want in plain English. The AI searches across weather, finance, demographics, sports, and public data repos to find the right dataset for your question.
Your Saved Datasets datasets you've uploaded or saved
Sample Datasets ready-to-use public-domain datasets
Public Data Repositories download CSVs to upload & analyse

Links to the best free, public-domain and open-licence data sources. Download any CSV and upload it to analyse it.

Kaggle Datasets ML-focused

The largest community of ML datasets. Millions of user-contributed datasets across every domain, most with kernels showing how to use them.

Visit →
UCI ML Repository ML-focused

The original academic benchmark repository. Over 600 clean, well-documented datasets used in thousands of research papers. Mostly public domain.

Visit →
Google Dataset Search Search engine

Google's dedicated search engine for datasets. Indexes millions of datasets from government portals, universities, and open repositories worldwide.

Visit →
OpenML ML-focused

Open platform built specifically for ML research. Datasets come with metadata, benchmark task definitions, and community benchmark scores for comparison.

Visit →
data.gov Government

The US federal government's open data portal. Over 300,000 datasets from agencies including the CDC, NOAA, USDA, and Census Bureau. All public domain.

Visit →
World Bank Open Data Government

Global development indicators for 200+ countries — GDP, health, education, poverty, trade, and climate. Excellent for regression and time-series modelling. CC BY 4.0.

Visit →
Our World in Data Research

Curated long-run datasets on health, energy, inequality, and population. Every chart links to a downloadable CSV. Exceptionally clean and well-documented. CC BY.

Visit →
AWS Open Data Registry Large-scale

Amazon's registry of large public datasets hosted on S3 — satellite imagery, genomics, weather, transport, and more. Many are too large to upload directly; use subsets.

Visit →
Harvard Dataverse Research

Academic research datasets deposited alongside published papers. Strong in social sciences, political science, and public health. Most are CC0 or CC BY.

Visit →
FiveThirtyEight Data Journalism

The data behind every FiveThirtyEight article — sports, politics, economics, and culture. Clean, analysis-ready CSVs. Great for building sports prediction models. CC BY 4.0.

Visit →
Hugging Face Datasets ML-focused

Over 50,000 datasets curated for NLP, CV, and tabular ML tasks. Download any dataset as a CSV or Parquet. Rapidly growing community with filtering by task, language, and licence.

Visit →
Zenodo Research

CERN's open-access repository for research data deposited alongside academic papers. 3M+ records across all scientific disciplines. Easily searchable and mostly CC BY or CC0.

Visit →
EUROSTAT Government

The EU's official statistical database — employment, inflation, trade, energy, and demographics for all EU member states. Excellent for cross-country regression analysis. CC BY 4.0.

Visit →
ProPublica Data Store Journalism

Investigative journalism datasets covering Congress, campaign finance, healthcare, criminal justice, and corporate lobbying. Many are unique datasets not found elsewhere. Free to download.

Visit →
Fetch from Public APIs 60 live data sources, no API key needed
Choose a data category