Construction Cost Prediction — ML models for forecasting project costs
Predict construction project costs with machine learning: Linear Regression, KNN, Random Forest, and Gradient Boosting on historical data — data preparation, feature engineering, model evaluation, and a reusable prediction pipeline with confidence ranges
- What
- Predict construction project costs with machine learning: Linear Regression, KNN, Random Forest, and Gradient Boosting on historical data — data preparation, feature engineering, model evaluation, and a reusable prediction pipeline with confidence ranges
- Cost
- Free
- Needs
- Python 3 with pandas, numpy, and scikit-learn (pip install pandas numpy scikit-learn) — your own historical project data (area, floors, building type, costs) to get real value
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @datadrivenconstruction's cost-prediction skill, listed here with credit to its creator (companion to the "Data-Driven Construction" book, chapter 4.5): forecast construction project costs from historical data using classical machine learning. It walks the agent through the full pipeline — preparing historical project datasets (missing values, categorical encoding, derived features like cost-per-m², inflation adjustment), feature engineering (interactions, polynomial features, log transforms, size binning), training and comparing Linear Regression, K-Nearest Neighbors (with GridSearchCV), Random Forest, and Gradient Boosting models with MAE/RMSE/R²/MAPE evaluation and cross-validation, then packaging the winner into a reusable prediction function with confidence ranges and joblib save/load. Honest caveats: predictions are only as good as the historical data — garbage in, garbage out; the worked examples are generic templates you adapt to your own schema; the inflation baseline is hardcoded to 2024 and needs updating; always present prediction ranges, not point estimates, for real budgeting decisions. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: Python 3 with pandas, numpy, and scikit-learn (pip install pandas numpy scikit-learn) — your own historical project data (area, floors, building type, costs) to get real value Install "Construction Cost Prediction — ML models for forecasting project costs" for me. It gives my agent @datadrivenconstruction's cost-prediction workflow: prepare historical project datasets (missing values, categorical encoding, derived features, inflation adjustment), engineer features, train and compare Linear Regression, KNN, Random Forest, and Gradient Boosting models with full evaluation (MAE, RMSE, R², MAPE, cross-validation), and package the best model into a reusable prediction pipeline with confidence ranges and joblib save/load. MIT licensed. Repository: https://github.com/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/blob/main/2_DDC_Book/4.5-ML-Cost-Prediction/cost-prediction/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "cost-prediction". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. pip install pandas numpy scikit-learn; prepare a CSV of my historical projects; update the 2024 inflation baseline; adapt feature names to my schema). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.