Skip to main content
Loading navigation
Back to challenges

Home Credit Risk & Renovation ROI Valuation Pipeline

Home improvement credit portfolios rely on accurately projecting post-renovation property value lift to manage collateral exposure. Build a machine learning valuation pipeline using LightGBM and pandas to predict post-renovation Automated Valuation Model (AVM) gains across home improvement categories. Achieve an R2 score of 0.88 or higher on post-renovation price predictions.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Develop a gradient boosting valuation pipeline using LightGBM to estimate post-renovation property value increases for home improvement loans.

How work is evaluated

Evaluation

Evaluates accuracy of post-renovation property value predictions.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

roi_match

Verifies calculated ROI percentage calculation.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

post_val_mae

Mean Absolute Error on predicted post-renovation property value. • target: 2500 • range: 0-20000

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Feature engineer home renovation categories (Kitchen, Bath, Roof, HVAC) and project costs

  • Train a LightGBM regressor predicting post-renovation appraisal values

  • Calculate project-specific Return on Investment (ROI) and value uplift ratios

  • Incorporate geographic micro-market appreciation trends into model training

Resources

Dataset notes

Dataset of paired pre- and post-renovation property appraisals, renovation costs, and renovation type categories.

Challenge setup

Evaluates accuracy of post-renovation property value predictions.

Challenge input

JSON object with pre_renovation_val, renovation_spend, renovation_type, Zipcode_appreciation_rate

LightGBM

Standard tabular machine learning library.

Evaluated output

JSON object with predicted_post_val, value_lift_usd, projected_roi_pct

Evaluation checks
  • Verifies calculated ROI percentage calculation.
  • Mean Absolute Error on predicted post-renovation property value. • target: 2500 • range: 0-20000
Configured evaluation evidence
  • Benchmark: AVMRegressionBench
  • Post Val Mae target: 2500
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Weights & Biases · Required
  • TPOT · Optional
  • Deepgram · Optional

Evaluation contract

  • roi_match · Weight 1
  • post_val_mae · Weight 1

Metrics

  • post_val_mae · Target 2500

Benchmarks

  • AVMRegressionBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with pre_renovation_val, renovation_spend, renovation_type, Zipcode_appreciation_rate

    Output: JSON object with predicted_post_val, value_lift_usd, projected_roi_pct

    Execution harness: Python

Evaluation tools

  • LightGBM · Gradient Boosting Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Home Credit Risk & Renovation ROI Valuation Pipeline