Radix Analytics Private Limited

Pricing

Airline passenger fare pricing has revolutionized airline management
Pricing advertising inventory on television works on same RM principles
Setting right offer price for truck freight on load-boards determines success of freight companies
An entirely different approach to pricing along with SKU features is used in the CPG world where novel items are born and get killed every other day
Housing finance needs to predict property prices given myriad features of properties and their surroundings

The trucking company was facing challenges in agreeing on right freight price with truck operators
Only a few skilled agents with knowledge of certain lanes could negotiate successfully
Suggest appropriate fare to be offered on load-boards for full truck loads (FTL) freight on a specific lane (Origin-Destination) for a particular date, equipment & load features, in the continental US market

Very sparse data: 70,000 loads (over 3 years), spread over 70 lanes and 42 equipment to answer a problem for any lane across the continent
Apparently erratic prices: e.g. OH-TX lanes (750-1200 mi) are priced same as IN-PA (500-600 mi), for same equipment!
Prohibitive price of historic data from Truckstop or DAT meant only generic third-party data like Fuel prices & CASS index

Ensemble modelling – A very large number of models were developed
A combination of very accurate localized models and broader hub-based models gave ~95% accuracy
Solution deployed using MLFlow, integrated with DataLake and transaction system

Advertisers buy certain audience for a budget – an agreement to buy advertising time (inventory) on properties and timebands at certain prices
Customizing these prices and inventory while ensuring overall fill across days & weeks, maintaining price/value of each property is a complex inventory fill monitoring and non-linear pricing & inventory allocation problem
Radix has developed Ad Revenue Optimizer (ARO) – a comprehensive software for broadcaster ad-revenue management

A budget airline wants to set prices competitively and ensure high fill rates on its routes
Using well-established Revenue Management principles, and airline & geography-specific nuances, Radix setup a system for forecasting yield and PAX at various DCPs for each flight-date
It has features like adjust PAX count pick-up trend
The forecast are run as nightly batches with possible manual triggers
Rolling forecast provide RPK, ASK reports etc.