We helped an NBFC realize dynamic
pricing recommendations through
a need-based pricing engine

The problem

Existing pricing decisions were taken heuristically, and the client wanted a more sophisticated, efficient and scalable methodology as:

• The current process did not take into account alternate drivers for pricing such as past customer purchase patterns and interactions
• Pricing recommendations were through market research (subjective) or manually by analyzing & tracking customer’s activity for each campaign
• The client wanted to capitalize on their data from previous markeitng campaigns and consumer transactions

Methodology

Customer profiling module - Used a combination of customer profile and historical transactions' data to calculate propensity of a customer to purchase the product.

Price Elasticity Model - ANN based price elasticity models with the primary target of profit maximization

Pricing Engine - Using price elasticity and customer propensity models, the engine is able to generate scenarios based on differential prices to arrive at the decision of pricing.

The solution has a feedback loop which takes into account customers' response to campaigns and this data is fed as input to the pricing engine for further refinement.

How did we enable consumption?

We helped the clients prioritize a set of financial products and associated campaigns to be launched as a part of the pilot run. Analyizing the results and response to these campaings, laid the ground work in further scaling the model systematically for other products across major markets/regions.

Our impact

Pricing experimentation carried out for the identified products led to incremental revenue realization of ~3. Understanding product drivers helped clients realize product differentiators. These helped the marketing team design a value-based personalized marketing campaign for the borrowers.