2019 - Dynamic Pricing for Airline Ancillaries with Customer Context - 小烨博客

Table of Contents

Problem Definition

Approach: 2 components
1. purchase probability model
2. revenue optimization model: given the purchase probability, recommend the optimal price that maximizes the expected revenue
Model
1. a two-stage
  1. purchase probability prediction
  2. Since price are within a range due business constrains -> map purchase probabilty to price
2. a two-stage model
  1. uses a deep neural network for forecasting
  2. coupled with a revenue maximization technique using discrete exhaustive search (define several pecentage beforhands)
3. a single-stage end-to-end deep neural network that recommends the optimal price with customized loss function
Result
1. We show that traditional machine learning techniques outperform human rule-based approaches in an online setting by improving conversion by 36% and revenue per offer by 10%.
Contribution
1. dynamic pricing using user specific info without violate customer privacy