← All projects

PROJECT 042 / 102 · Materials

Strength prediction by curing age.

At which curing ages are the fixed strength model errors largest?

Focused analytical studyConcrete strengthExecuted notebook

THE RESULT

What the data shows

The largest computed metric is 5.489 for (28.0, 90.0]; the smallest is 3.128 for (0.0, 7.0]. Metric: mae (MPa MAE).

Small holdout groups make age-specific averages unstable; this is a diagnostic, not a new independent test.

Strength prediction by curing age — chart from the computed study output
Computed study output. Full values and units are available in the results download.
Computed results · 4 of 4 rows. Values rounded for display; source units and raw column names are retained in the download.
bandtest samplesmae
(0.0, 7.0]473.128
(28.0, 90.0]275.489
(7.0, 28.0]954.501
(90.0, inf]254.775
Download the complete result table ↓

THE METHOD

From source to answer

Stratify grouped-holdout residuals by prespecified curing-age bands.

The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.

EVALUATION

How the result was checked

Fixed 80/20 split of unique input groups (seed 42); exact input duplicates stay together.

836Training observations
194Test observations

Fixed configurations specified before scoring; no tuning on the holdout.

Target and input features

Target: strength

Inputs: cement, slag, fly_ash, water, superplasticizer, coarse_aggregate, fine_aggregate, age

Download evaluation record ↓

THE NEXT DECISION

What follows from the finding

Review error patterns across testing ages when specifying an external validation study.

Where the conclusion stops

Laboratory observations do not certify a construction mix. Composition and curing conditions are confounded. Models require independent engineering validation and cannot replace strength testing.

Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.