Skip to main content
Back to challenges
Challenge

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
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

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

Delivery guide

How work is evaluated

Evaluation

Evaluates accuracy of post-renovation property value predictions.

Datasets

Challenge datasets

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

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

What you should walk away with

  • 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 and assets

Reference links and supporting material

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)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured 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