Neural network demand models and evolutionary optimisers for dynamic pricing

Shakya, Siddhartha; Kern, Mathias; Owusu, Gilbert; Chin, Choong Ming

doi:10.1016/j.knosys.2011.06.023

Cited by 26 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Demand prediction models are usually used by retailers for solving various problems including optimal price setting (e.g. [10], [11], [31], [18], [28]), sales volume forecasting (e.g. [17], [14], [4], [5], [27]), effective stock management ( [1], [3]) and many others.…”

Section: Literature Reviewmentioning

confidence: 99%

The Ensemble Method for Censored Demand Prediction

Evgeniy

Владимировна

2018

SSRN Journal

View full text Add to dashboard Cite

Many economic applications including optimal pricing and inventory management requires prediction of demand based on sales data and estimation of sales reaction to a price change. There is a wide range of econometric approaches which are used to correct a bias in estimates of demand parameters on censored sales data. These approaches can also be applied to various classes of machine learning models to reduce the prediction error of sales volume. In this study we construct two ensemble models for demand prediction with and without accounting for demand censorship. Accounting for sales censorship is based on the idea of censored quantile regression method where the model estimation is splitted on two separate parts: a) prediction of zero sales by classification model; and b) prediction of non-zero sales by regression model. Models with and without accounting for censorship are based on the predictions aggregations of Least squares, Ridge and Lasso regressions and Random Forest model. Having estimated the predictive properties of both models, we empirically test the best predictive power of the model that takes into account the censored nature of demand. We also show that machine learning method with censorship accounting provide bias corrected estimates of demand sensitivity for price change similar to econometric models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

The Ensemble Method for Censored Demand Prediction

Evgeniy

Владимировна

2018

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…However, in the last few years, dynamic pricing has increasingly adopted and successfully operated in terms of evolving pricing policy in hotel industry [2,5]. Dynamic pricing is defined as a strategy to model the effect between the price for a product or service on the specific period and price along the planning horizon or known as demand model [6].…”

Section: Introductionmentioning

confidence: 99%

Online Travel Agency Channel Pricing Policy based on Dynamic Pricing Model to Maximize Sales Profit Using Nonlinear Integer Programming Approach

Shadiqurrachman¹,

Ridwan²,

Kusuma³

2019

Proceedings of the 2019 1st International Conference on Engineering and Management in Industrial System (ICOEMIS 2019)

View full text Add to dashboard Cite

A dynamic pricing strategy on the cooperation between a hotel and an online travel agency (OTA) is commonly applied to build a pricing policy. The purpose of this study is to propose a pricing policy according to the dynamic pricing model on a single online travel agency channel. The paper provides a dynamic pricing model adjusted to hotel problems with multiple room types. The study consists of two stages. First, we apply a revenue management tool that is dynamic pricing to model the effect of price on demand. The price dynamically changes based on the parameter of demand model. Second, we use a nonlinear integer programming approach to maximize the profit by substituting the demand model which has the lowest root mean square error. The parameter of the demand model is estimated by using the historical sales-price data from one of the hotels in Bandung, West Java, Indonesia. Our results propose a pricing policy of each room types that able to increase 18.54% from the historical sales profit. The proposed pricing policy completes the gap of the method in the existing pricing policy. Moreover, the findings provide an optimal room rate to the front office manager along the planning horizon.

show abstract

“…Most of the research on using neural network in the revenue management models concentrate on forecasting the demand [21][22][23][24][25][26][27][28][29][30]. Volling et al [31] used neural network for approximating the opportunity cost of resources.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Choice-Based Network Revenue Management

Etebari

Najafi

2016

Scientia Iranica

View full text Add to dashboard Cite

Abstract. Choice-based network revenue management concentrates on importing choice models within the traditional revenue management system. Multinomial logit is a popular and well-known model which is the basic choice model in revenue management. Empirical results indicate inadequacy of this model for predicting itinerary shares; therefore, more realistic models, such as nested logit, can be proposed for substituting it. Incorporating complex choice models in the optimization module based on statistical tests without considering the complexity of the obtained mathematical model would lead to increase in the complexity of a system without obtaining signi cant improvement. Considering the in uence of discrete choice model on the structure of optimization model, it is necessary to analyze the interaction between speci c discrete choice and optimization models. In this paper, a knowledge acquisition subsystem is introduced for providing intelligence and considering the most suitable choice models. We develop the feedforward multilayer perceptron arti cial neural network for forecasting revenue improvement percent obtained by using more realistic choice models. The obtained results demonstrate that the new system will decrease the complexity of the system, simultaneously, while preserving revenue of the rm. According to the computational results, by increasing the resource restriction, the process of incorporating more realistic choice model will be more important.

show abstract

Neural network demand models and evolutionary optimisers for dynamic pricing

Cited by 26 publications

References 14 publications

The Ensemble Method for Censored Demand Prediction

The Ensemble Method for Censored Demand Prediction

Online Travel Agency Channel Pricing Policy based on Dynamic Pricing Model to Maximize Sales Profit Using Nonlinear Integer Programming Approach

Intelligent Choice-Based Network Revenue Management

Contact Info

Product

Resources

About