Sales Territory Optimizer
Assign accounts to sales representatives optimizing for workload balance, travel efficiency, and revenue coverage. Upload your data, run optimization algorithms, or manually draw territories and compare outcomes.
OVERVIEW & WHAT THIS TOOL SOLVES
Carving up sales territories by arbitrary state lines or postal codes leaves one rep drowning in 80 accounts while another starves with 20, or forces reps to crisscross each other's highways every week. The Sales Territory Optimizer partitions customer accounts across sales representatives using spatial clustering and capacity-constrained optimization—balancing account workload, minimizing windshield travel distance, and aligning high-potential accounts with rep capacity.
🎯 Questions It Answers
- How should we assign accounts to sales reps so every territory has balanced revenue potential and manageable travel distance?
- How do Balanced K-Means, Greedy Nearest-Neighbor, and Weighted Voronoi partitioning compare on our account map?
- What happens to workload equity and total travel miles if we manually reassign key accounts or move a rep's home base?
📂 What Data You Need
- Account Locations & Value: Coordinates (lat/lon or X/Y), deal potential or revenue weight (
w_j), and workload hours - Sales Rep Roster: Rep home-base coordinates (
μ_i), capacity limits (C_i^{max}), and skill/performance weights - Optimization Priority Sliders: Relative weights on travel distance, workload balance, and revenue alignment
💡 What You'll Discover
- Interactive Territory Map: Convex hulls, rep-to-account assignment lines, and manual lasso/click reassignment
- Equity & Efficiency Scorecard: Coefficient of variation in workload, average travel distance, and composite quality score
- Rep-by-Rep Breakdown: Account count, total pipeline potential, capacity utilization, and travel burden per rep
🔍 Key Nuances & Common Traps to Watch For
- Pure Nearest-Neighbor Creates Starving and Overloaded Reps: Assigning every account to the closest rep ignores urban density—downtown reps get 3× their capacity while suburban reps sit idle. Balanced K-Means enforces capacity ceilings during assignment.
- Equal Account Counts ≠ Equal Workload: Twenty enterprise accounts worth $250K each require far more selling hours than twenty SMB accounts worth $10K. Always weight territories by potential revenue or service hours (
w_j). - Human Override on Relationships: Optimization gives the mathematical starting line, but existing executive relationships matter—use the manual reassignment tools to lock key accounts and see the exact travel/balance trade-off.
📐 Under the Hood: Model Equations & Variable Definitions
1. Capacity-Constrained Weighted K-Means Objective
💬 Read it in plain English: Assign each account j to a rep territory C_i to minimize total value-weighted squared travel distance from the territory center μ_i, without exceeding any rep's maximum account capacity M_i.
2. Multiplicative Weighted Voronoi Distance & Workload Balance
💬 Read it in plain English: Weighted Voronoi divides physical distance by rep influence weight ψ_i so higher-capacity reps pull from a wider radius, while the coefficient of variation CV_W measures territory workload inequality (lower is fairer).
DATA INPUT MODE
Explore pre-built marketing scenarios with realistic account and rep data.
DATA SOURCE
Use a Case Study
Select a scenario above to load realistic account and sales representative data, or upload your own CSV files.
Advanced settings
Upload Your Data
Accounts / Prospects
CSV with account locations, potential value, and close probability.
Drag & Drop accounts file
.csv or .tsv with headers
Sales Representatives
CSV with rep locations, capacity constraints, and effectiveness.
Drag & Drop reps file
.csv or .tsv with headers
TERRITORY MAP
Load data to see territories