Skip to main content
Back to challenges
Challenge

Casino Foot-Traffic Heatmap & Non-Gaming Revenue Spatial Predictor

Adapting casino layouts to dynamic non-gaming demand requires analyzing sensor foot-traffic clusters. Build a spatial clustering pipeline using Scikit-Learn (DBSCAN / K-Means) to process anonymized optical sensor locations and forecast high-conversion retail placements. Deliver spatial clustering visualizations in under 10 seconds.

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.

Construct a spatial foot-traffic clustering pipeline using Scikit-Learn to identify high-yield placement zones in commercial properties.

Delivery guide

How work is evaluated

Evaluation

Evaluates spatial clustering accuracy and dwell hotspot identification precision.

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

Cluster Count Verification

Must detect 2 distinct coordinate clusters

Binary check

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

Dimension 2

Centroid Distance Error

Euclidean distance between predicted and exact hotspot centroid • target: 0.05 • range: 0-1

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

  • Ingest 2D coordinate telemetry streams from overhead optical sensors

  • Apply DBSCAN and K-Means clustering algorithms to detect customer dwell hotspots

  • Map foot-traffic density clusters to spatial non-gaming yield metrics

  • Output optimal locations for new dining, lounge, and retail popup concepts

Resources and assets

Reference links and supporting material

Dataset notes

Anonymized 2D spatial coordinate telemetry from overhead optical sensors in commercial venues.

Challenge setup

Evaluates spatial clustering accuracy and dwell hotspot identification precision.

Challenge input

JSON with sensor_points (array of [x,y]), eps, min_samples

Scikit-Learn

Provides spatial clustering algorithms (DBSCAN, K-Means)

Evaluated output

JSON with cluster_count, primary_hotspot_centroid

Evaluation checks
  • Must detect 2 distinct coordinate clusters
  • Euclidean distance between predicted and exact hotspot centroid • target: 0.05 • range: 0-1
Configured evaluation evidence
  • Benchmark: SpatialClusterBench
  • Centroid Distance Error target: 0.05
  • 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
  • Zed · Required
  • Anon · Optional
  • Twin · Optional

Evaluation contract

  • Cluster Count Verification · Weight 1
  • Centroid Distance Error · Weight 1

Metrics

  • Centroid Distance Error · Target 0.05

Benchmarks

  • SpatialClusterBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with sensor_points (array of [x,y]), eps, min_samples

    Output: JSON with cluster_count, primary_hotspot_centroid

    Execution harness: Python

Evaluation tools

  • Scikit-Learn · Machine Learning Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Casino Foot-Traffic Heatmap & Non-Gaming Revenue Spatial Predictor