Case Studies
Analytical systems built for real business problems.
A selection of analytical engagements across retail, logistics and financial services — showing how rigorous methodology translates into measurable business improvement.
Demand forecasting system that reduced inventory costs by 28%
A mid-size European retailer with 47 locations and 12,000 SKUs moved from manual demand planning to a hierarchical ensemble forecasting system — cutting stockouts, eliminating excess inventory and improving planning accuracy across the full catalog.
Forecast error reduction
38% → 21% MAPE (44% improvement)
Stockout reduction
−67% during promotional periods
Excess inventory reduction
−29% carrying costs
Annual cost improvement
€2.8M estimated benefit
Route optimization system delivering 17% efficiency improvement across 82-vehicle fleet
A regional logistics operator replaced manual routing with a mathematical optimization engine, dramatically improving on-time delivery performance, cutting fuel costs and freeing dispatcher capacity for higher-value work.
Route efficiency improvement
+17% (km per delivery)
Fuel cost reduction
−14% in first 6 months
On-time delivery performance
78% → 91%
Dispatcher planning time
2.5 hours → 35 minutes/day
ML-based risk scoring model reducing default rates by 44%
A specialty lending institution replaced rules-based credit assessment with a two-stage ML scoring system, dramatically improving default prediction accuracy and reducing decision time from 4.2 days to 6 hours.
12-month default rate
8.7% → 4.9% (−44%)
Application decision time
4.2 days → 6 hours
Underwriter consistency
Gini 0.61 → 0.89
Early warning accuracy
73% of defaults flagged 90+ days early