AutoML without uploading raw CSV data
Upload-first AutoML can be inconvenient when the data is private, early, messy, or not yet approved for cloud processing. MLdeck offers a browser-local normal training flow for CSV exploration, so users can profile data, train tabular models, review metrics, and export artifacts without raw CSV cloud upload during the normal browser training process.
The problem with upload-first AutoML
Upload-first AutoML asks users to move raw training data into a hosted system before they know whether the dataset is useful. That creates friction. A CSV may contain customer records, financial rows, operational details, patient-like attributes, employee information, or proprietary business metrics. Even when the dataset is ultimately safe to process externally, the early exploration phase is often full of uncertainty.
Teams may ask basic questions first: is the target usable, are there enough rows, are categories meaningful, are missing values concentrated in a time period, is the data sorted, and are there columns that leak the answer? It is reasonable to answer those questions with less data movement. AutoML without uploading raw CSV data is about shifting early exploration closer to the user's device and delaying heavier infrastructure decisions until the dataset has earned them.
How browser-local training changes the workflow
MLdeck brings the training workflow to the browser. Instead of sending the CSV to a cloud training job, the app parses and profiles the file locally, lets the user select features and a target, and fits candidate tabular models using browser-executed tooling. During normal browser training flows, raw CSV rows are not uploaded to a cloud training service.
This does not mean every part of the product is disconnected from backend services. Account, app, support, billing, security, and control-plane features may use backend infrastructure. The important distinction is that normal CSV training does not require raw CSV cloud upload for model fitting.
What MLdeck does locally
MLdeck's browser workflow covers the practical pieces of early tabular modeling. It profiles columns, estimates data types, shows missingness and cardinality, supports feature inclusion decisions, helps identify targets, fits classification or regression candidates, displays leaderboard evidence, and prepares export artifacts. Users can inspect warnings and decide whether the dataset is ready for more serious validation.
The local approach also helps education. Students can open a CSV and see how preprocessing affects model evidence without installing Python, configuring notebooks, or receiving cloud credentials. Analysts can test a hypothesis before asking for engineering help. Developers can produce an ONNX artifact for parity checks before designing a serving system.
What still requires caution
Privacy-first architecture does not remove user responsibility. Your browser, extensions, operating system, local storage policies, downloaded reports, exported models, and shared files all matter. If a CSV is sensitive, derived artifacts may also be sensitive. A model can encode patterns from source data, and a PDF report may include metrics or field names that should be handled carefully.
MLdeck is an MVP and early beta. It is suitable for exploratory modeling and early evaluation, but strict validation should be used before relying on results for important decisions. Users working with regulated or high-impact data should follow internal review procedures and legal guidance.
Practical checks include using a trusted browser profile, closing unneeded extensions, confirming the file is allowed for local analysis, and deciding where exported artifacts will be stored after download. The browser-local training flow is one part of a broader data handling process.
Exporting results without locking data into a cloud platform
One benefit of a browser-first workflow is that the result is not tied to a proprietary hosted endpoint. MLdeck can export ONNX artifacts designed for portable ONNX Runtime inference, subject to parity validation. It can also produce Docker packages for deployment testing and PDF reports for review. These artifacts support a workflow where early exploration stays local and later validation can happen in an environment chosen by the user.
Exports should not be treated as automatic approval for deployment. Use them as testable artifacts. Check input schema, preprocessing metadata, validation samples, behavior across representative rows, and monitoring requirements before moving toward production systems.
AutoML without uploading data FAQ
Can AutoML work without uploading data?
For many CSV exploration workflows, yes. MLdeck runs normal training flows in the browser without raw CSV cloud upload.
What data leaves my browser during MLdeck training?
Raw CSV training rows are processed locally during normal browser training flows. Backend services may still support app, account, or control-plane features.
Are downloaded exports safe to share?
Treat them as derived artifacts. Review model files, schemas, and reports before sharing, especially if the source data is sensitive.
Does MLdeck replace cloud AutoML?
No. It is useful for learning, early evaluation, and private exploration. Larger governed workflows may still require dedicated infrastructure.
What should I check before using sensitive datasets?
Review local device security, browser extensions, organizational approval, downloaded artifacts, and validation responsibilities.
Explore browser-local AutoML topics
Continue with guides and examples about privacy-first design, CSV workflows, and browser ONNX export.