Machine Learning based Framework for Robust Price-Sensitivity Estimation with Application to Airline Pricing

The paper proposes a machine learning-based framework for robust price-sensitivity estimation in the context of dynamic pricing of products with feature-dependent price sensitivity. The authors construct a demand model using a Poisson semi-parametric approach, where the price-related part is parametric and the remaining (nuisance) part is non-parametric and modeled using sophisticated ML techniques. To address potential biases in nuisance parameters, they propose a two-stage estimation methodology that makes use of deep neural networks or other sophisticated ML estimators to construct estimators of observed purchases and prices given feature vectors. In the second stage, they leverage a Bayesian dynamic generalized linear model to estimate the price-sensitivity parameters using these estimators. The proposed framework is tested on simulated and real sales transaction data from the airline industry, demonstrating its superiority over direct one-stage approaches in terms of accuracy of estimates. Additionally, it has several advantages over existing methods such as flexibility and interpretability due to its semi-parametric nature as well as ability to handle complex interactions between features and prices while being robust to biases in nuisance parameters. This paper contributes to improving pricing strategies by providing an accurate method for estimating price-sensitivity parameters in dynamic pricing models which could be applied beyond airline pricing to other industries where dynamic pricing with feature-dependent price sensitivity is relevant.

A Machine Learning-Based Framework for Robust Price-Sensitivity Estimation

Dynamic pricing has become increasingly popular in recent years, with many companies using it to maximize their profits. The success of dynamic pricing depends on the ability to accurately estimate price sensitivity parameters, which are used to determine how customers will respond to different prices. Traditional methods of estimating these parameters have been limited by their inability to handle complex interactions between features and prices or account for potential biases in nuisance parameters.

In this paper, the authors propose a machine learning-based framework for robust price-sensitivity estimation in the context of dynamic pricing of products with feature-dependent price sensitivity. This framework consists of two stages: first, they construct a demand model using a Poisson semi-parametric approach where the price related part is parametric and the remaining (nuisance) part is non-parametric and modeled using sophisticated ML techniques such as deep neural networks; second, they leverage a Bayesian dynamic generalized linear model to estimate the price sensitivity parameters using these estimators.

The proposed framework was tested on simulated and real sales transaction data from the airline industry. Results showed that it outperformed direct one-stage approaches in terms of accuracy of estimates while also being more flexible and interpretable due its semi-parametric nature as well as having better ability to handle complex interactions between features and prices while being robust against biases in nuisance parameters.

This research contributes significantly to improving pricing strategies by providing an accurate method for estimating price sensitivity parameters in dynamic pricing models which could be applied beyond airline pricing into other industries where dynamic pricing with feature dependent price sensitivity is relevant.