Readiness summary
A quick view of whether the file looks ready, needs attention, or has high-risk review signals.
Data Quality report template for CSV review
A Data Quality report helps summarize browser-local CSV profiling signals in a readable format for review and discussion.
It is useful for communicating findings, but it does not certify correctness, privacy status, compliance, or model performance.
What the report is useful for
The browser-local report is designed to help teams discuss a CSV before deeper work. It can summarize profile signals, readiness level, issue categories, top review areas, and recommendations in language that non-ML users can read.
That makes it helpful before a cleanup meeting, stakeholder review, handoff to an analyst, or an AutoML experiment.
What it can contain
Profile overview
Row and column counts, detected column groups, and browser-local profiling notes.
Issue list
Missingness, schema, identifier, constant-column, and other review signals when present.
Recommendations
Practical next steps for documentation, cleanup, sharing, or deciding whether AutoML is appropriate.
What it does not guarantee
The report is not a full audit. It does not automatically clean data, prove a CSV is correct, certify privacy or compliance, or prove that a future model will perform well.
Use it as a starting point for review. Important decisions still need domain context, validation, and careful handling of the original file.
Browser-local reporting
MLdeck Data Quality is designed so the CSV review and report generation happen in the browser. The report should communicate what was observed, not create stronger proof than the underlying profile supports.