Lane Mix Optimization


Situation: A Global Cosmetics Major's US Operations (NE Division) needed help in reducing their transportation costs.

Approach: After a detailed diagnostic analysis, we identified that the carrier mix and the mode mix were sub-optimal - with lower rate carriers being less used and LTL contributing to > 70% of the total shipments.
We built a model, to provide them with an optimal mode-mix and carrier selection options, depending on the demand at a lane level.

Results: The model provided 17% savings on transport cost and a proof-of-concept for the client, to replicate across the rest of US.


Client: Global Cosmetics Top 2 Company
Duration: 1.5 Months
Tags: Transportation, Mode-Mix Optimization
Lane Mix Optimization at a Global Cosmetics Manufacturer and Distributor

Route Scheduling: Major US trucking company


Situation: he client was a 3rd party transportation carrier with a large fleet of trucks and more than 50,000 drivers on their roster. They had uncertain demand and needed a tool to optimize demand allocation and reduce transportation costs.

Approach: We identified the key drivers of cost as - Fuel Costs (per mile), Maintenance Costs (total miles driven) and Driver's Salaries (per hour). Our multi-objective optimization model factored in these major costs in the objective function and multiple constraints like driver hours, # of pit-stops, service levels etc. We identified key themes of opportunities/cost leakages and offered options to the model accordingly.

Results: The client identified savings of ~12% on their overall costs in scope. They are using the model as a blue-print to design a IT solution for real-time implementation.


Client: A major trucking company in the US
Duration: 1 Month
Tags: Logistics

Existing Customer Pricing


Situation: As a follow-on from the customer segmentation, which helped pin-point low profitability segments, the client wanted to redress the situation by targeted price increases, while minimizing the volume impact.

Approach: We worked with the Client's Sales data to identify pricing patterns and the corresponding impact on volumes. Identified pockets of customers and distinct price points with low profitability and minimal risk of churn. We also built a statistical model to identify "fair price" based on market parameters and proposed a staggered increase of prices to different sets of customers.

Results: After implementing a staggered price increase for a year based on our recommendation, the client has improved his net profitability by ~15% on about a fifth of his overall customer base.


Client: A $300M Real Estate Player in South India
Duration: 4 Months
Tags: Pricing