Train ML models in your browser

The workflow at a glance

CSV → Profile → Select target → Train → Compare → Report / Export. CSV profiling and data-quality warnings run automatically before training — no separate tool needed.

Why train ML models in the browser

Training in the browser changes the first step of machine learning. Instead of installing Python, creating a notebook environment, setting up packages, or uploading a CSV to a cloud service, a user can open a web page and begin. MLdeck is a live browser-local AutoML product for practical CSV-based machine-learning workflows: users can understand which columns are useful, which target makes sense, what warnings appear, and whether a simple model has signal.

Browser ML training is useful for people who need fast feedback. Analysts can test ideas, students can learn by doing, developers can generate ONNX-oriented export packages for validation, and data scientists can compare quick baselines before writing custom code.

During normal browser training workflows, raw CSV data is not uploaded to MLdeck servers. The browser ML runtime itself may be downloaded from a CDN at training start — a code download, not a data upload. See the privacy-first page for details.

Step-by-step browser ML workflow

A typical MLdeck session begins with a CSV upload in the browser. The app profiles the dataset, summarizes columns, and helps the user review feature choices. Next, the user selects a target column and confirms the task. MLdeck can then train candidate models for tabular classification or regression, depending on the target and schema.

After training, the user reviews leaderboard evidence, metrics, warnings, and export readiness. This sequence is meant to make modeling decisions visible. It encourages the user to ask whether the target is valid, whether important features are missing, whether the first rows are biased, whether class balance changed later in the file, and whether the evaluation strategy matches the real use case.

Before and after training

Before training, use the CSV Data Quality Checker or the Data Quality for Machine Learning guide to review missing values, schema consistency, leakage risk, identifiers, and target imbalance. That makes the browser-local training step easier to interpret.

After training, read the result as AutoML validation evidence, not as a final approval. Reports and AutoML export artifacts can support external testing, schema review, and user-side verification.

What algorithms and tasks MLdeck supports

MLdeck focuses on tabular classification and regression workflows. It can compare several scikit-learn style model families, including linear models and tree-based candidates where supported by the browser workflow. The available choices may depend on task type, selected features, data size, browser resources, and runtime support.

This focus is intentional. CSV AutoML is most useful when the problem is structured: predict a category, estimate a numeric outcome, compare feature influence, or evaluate whether a table has learnable signal. It is not a general deep learning workbench, image trainer, large language model trainer, or replacement for every cloud ML platform.

That narrower scope helps keep the workflow understandable. Users can see the target, features, preprocessing, metrics, and export contract in one place.

How evaluation evidence should be interpreted

Metrics are evidence, not permission slips. A high score may come from leakage, sorting, repeated entities, class imbalance, or a target that is easier in the sample than in the future. A low score may mean the data lacks signal, the target is noisy, the split is wrong, or preprocessing needs review. MLdeck surfaces warnings and evidence to support better judgment.

MLdeck combines browser-local training with baseline comparison, data-quality warnings, leakage-risk warnings, and modular validation evidence. Use those signals together with representative holdouts, temporal validation where relevant, export parity checks, and domain review.

Users should also ask whether the model will see the same kind of rows later. If the CSV was sorted by time, filtered to successful cases, or collected from a narrow period, the metric may overstate how the model behaves in a broader setting.

Exporting models and reports after training

After training, MLdeck can create exportable artifacts. ONNX-oriented export packages are generated from browser-local training workflows and are designed for ONNX Runtime testing with schema, manifest, and parity-review metadata. Docker packages can help test an API-style serving path. PDF reports can document metrics, warnings, and preprocessing. Python artifacts can help technical users inspect or extend the workflow.

Exports are useful because they turn an in-browser experiment into something that can be checked elsewhere. Teams can validate schema, representative rows, error handling, and runtime behavior in their chosen environment.

Browser ML training FAQ