Pricing Optimization
Set profit-maximizing prices across products and channels, factoring in demand elasticity, competition, inventory, and business constraints.
NP-hard (discrete), Convex (continuous)Complexity
Why Pricing Optimization Is Hard
Nonlinear demand response
Demand doesn't decrease linearly with price. The demand curve bends, shifts with competition, and varies by customer segment and season.
Cross-product effects
Changing the price of milk affects bread sales. These cross-elasticities create a web of interdependencies across thousands of SKUs.
Discrete price points
Real prices end in .99 or .49. This discreteness turns a smooth optimization problem into a combinatorial one with far more possible solutions.
Real-World Example
What This Looks Like in Practice
A retailer manages 5,000 SKUs across online, in-store, and wholesale channels. A competitor just dropped prices on 200 high-visibility products. The optimal response isn't matching on those 200. It's adjusting prices across a carefully selected subset of all 5,000 SKUs to maximize total margin. That's 15,000 decision variables (5,000 SKUs times 3 channels) with nonlinear demand functions and cross-product effects.
Approach
How kint Solves Pricing Optimization Problems
Estimate demand elasticity
ML models learn how demand responds to price changes, competitor actions, and seasonal effects from your historical sales data.
Formulate the pricing model
Price decisions become variables. Margin targets, channel consistency rules, and competitor matching rules become constraints.
Solve with NLP or MIP
Nonlinear programming for continuous prices. MIP for discrete price points like €X.99. kint selects the right formulation.
Daily re-optimization
New competitor data, sales figures, and inventory levels trigger re-optimization. Prices stay current automatically.
Technical Details
Pricing optimization is formulated as nonlinear programming when demand functions are nonlinear, or as mixed-integer programming for discrete price points. kint integrates ML-based demand elasticity estimation with mathematical optimization for the pricing decision.
Impact
What Changes
Gross margin
Baseline
+7%
Revenue
Baseline
+3%
Pricing response time
2-3 days
Same day
Dead stock
15% of inventory
11.4% (-24%)
Price consistency
Manual channel checks
Guaranteed by constraints
Example
Input
Optimize prices for 5,000 SKUs across 3 sales channels with competitor price matching and minimum margin constraints.
Output
Optimal price matrix with 7% higher gross margin, 3% revenue increase. Updated daily.
+7%
gross margin
+3%
revenue
5000 SKUs
optimized
Connections
Related Problem Types
Have a Pricing Optimization Problem?
Show us your data. We'll show you what optimal looks like. No commitment.