Journal of Revenue and Pricing Management最新文献

Analytical models (AM) and machine learning (ML) models are often considered to be at opposite ends of the modeling spectrum. AM are closed form expressions based on first principles which require deep domain knowledge and are difficult to construct but can extrapolate to unseen data and are data-efficient and interpretable. At the other end, ML models require little or no domain knowledge to construct, are flexible, and can provide superior accuracy in data-rich environments, but cannot extrapolate, are data-inefficient and are black boxes. We investigate how to consolidate these opposite views to obtain the best of both worlds in the context of airline demand forecasting. We leverage on an existing AM baseline and employ deep learning-based ML models as correctional multiplicative factors. This approach provides a transparent, interpretable hybrid model with a forecast accuracy outperforming both pure AM and pure ML models.

Selling fresh food products can be challenging due to their perishability, which often results in significant losses. To address this issue and maximize profits, we have developed a contract that takes into account the costs of investing in preservation technology over a finite planning horizon. The arrangements incentivize the supplier and the retailer to establish coordination and determine not only the optimal price and schedule for replenishment but also the optimal investment required in preservation technology. We investigate the effectiveness of vendor managed inventory (VMI) and consignment with revenue-sharing models through an analysis of pricing and inventory decisions, followed by evaluating the channel performance and the distribution of profits. Contract parameters are defined under the equilibrium state to achieve advantageous relationships among supply chain partners by improving profits for both channel members. The finding shows that a VMI and consignment mechanism with a side payment arrangement could help coordinate channels in a non-cooperative setting. Still, performing the contract is easier in a cooperative setting. Both members could achieve optimal decisions for the wide-channel system without any additional payments, leading to increased profitability for all supply chain members. In an alternative approach, the retailer has the option to offer a subsidy alongside the revenue-sharing-only trading terms within a VMI and consignment by incorporating a generalized revenue-sharing scheme to facilitate coordination with the supplier.

Dynamic Airline ticket pricing is a complex process, wherein airlines determine the best price for varied business contexts that encapsulate several factors. While most airlines use traditional revenue management (RM) systems to do this, studies have shown that deep reinforcement learning (DRL) models could maximize revenue by expanding price discovery. However, scaling these models to all routes of an airline would be cost-intensive. To help address this issue, we propose the application of transfer learning to share the knowledge gained from DRL, between similar routes, potentially helping airlines inch closer to putting a DRL-based pricing-model in production.

Price fluctuations largely influence consumers’ purchasing behavior in two opposite directions: they affect price sensitivity and the acceptable price ranges, while favoring consumers to exhibit strategic behavior by waiting for prices to come back down. Firms selling revenue-managed goods can exploit this tradeoff to efficiently implement revenue management practices. We illustrate how to incorporate price volatility into the classic Expected Marginal Seat Revenue model. Our results reveal that, in certain market conditions, such integration could result in a significant increase in revenue. We further provide guidance to support pricing decisions when faced with the price sensitivity—strategic consumers tradeoff.

This research aims to identify how fine dining restaurants can effectively implement reservation cancellation policies to address the issue of no-shows by applying equity theory, the dual entitlement principle, and social cognitive theory. Two experiments identified cancellation policy elements that influence restaurant evaluations and reservation behaviors. Findings revealed that cancellation policies negatively influence restaurant evaluations, and that policy strictness and awareness can attenuate this relationship via perceived fairness while enhancing the likelihood to book reservations and honor reservations. This research suggests that restaurants can benefit from implementing lenient cancellation policies and introducing awareness of the adverse impact of no-shows to customers.

Economic exploitation of power systems has always been significant in the electricity industry. However, after restructuring the systems above and separating different sectors of this industry into independent enterprises, economic profitability became twice as important. In this paper, the issue of electricity pricing is examined from a retailer’s point of view. The retailer supplies electricity from various sources, including the electricity market, bilateral contracts, and renewable sources, and then tries to sell it to customers at the optimal price. Here, the objective function combines expected profit and the conditional value at risk as a risk measure. Because of demand responsiveness, the retailer can use pricing tools to manage customer demand. Besides customer demand, the electricity market price and power generation of renewable energy sources are stochastic, and the advantage of the chance-constrained programming approach is taken to cover the power balance risk. Eventually, a hybrid chance-constrained and scenario-based method is proposed to model the retail electricity pricing problem based on fixed and real-time pricing policies. Furthermore, the energy storage system is considered a tool to increase the expected profit and control environmental effects; pollution costs are considered for electricity supplied from non-renewable sources. The proposed model maximizes profit and reduces environmental effects by considering pollution costs. To show the effectiveness of the proposed model, a numerical example is presented and solved. Results show that profit is maximized by determining each source’s optimal selling price and power. Meanwhile, the energy storage system simultaneously increases this profit.

Accurately forecasting demand poses challenges for revenue managers, especially amid supply and demand uncertainties increased by the recent global pandemic. In addition, demand forecasting is particularly challenging in the hotel industry due to anomalous days and repeating seasonal patterns. This study investigates techniques like TBATS, MSTL, and STL Decomposition against Linear Regression in hotel demand time series analysis, focusing on daily occupancy and average daily rate seasonalities. Using a 5-year dataset from an Upper Upscale branded property, the study employs in-sample data for model development and a rolling window approach for testing. Results highlight the robust performance of TBATS and MSTL across different forecasting horizons, consistently outperforming Seasonal-Trend Decomposition (STLF) and linear regression, providing insights crucial for revenue optimization and strategic decision-making in the hotel industry.