{"title":"以促销定价策略为主要需求驱动因素的零售业销售预测混合模型","authors":"Naragain Phumchusri, Nichakan Phupaichitkun","doi":"10.1057/s41272-024-00477-7","DOIUrl":null,"url":null,"abstract":"<p>The implementation of promotional pricing strategies constitutes a key component within the realm of retail revenue management. Nonetheless, the accurate prediction of sales in the presence of price discounts proves challenging due to the influence of various factors that contribute to demand uncertainty and high fluctuations. This study aims to find the most suitable prediction models for retail product unit sales while comprehensively accounting for the complex impacts of contributing factors. The dataset, sourced from a case study of a retail company, spans the temporal interval from January 2020 to December 2022. The predictive models, encompassing linear regression, random forest, XGBoost, artificial neural networks, and hybrid machine-learning models, are systematically developed. Then, the identification of the most suitable model is facilitated through the computation and comparative analysis of the Mean Absolute Percentage Error, with due consideration given to the weighting by the respective product’s revenue, thereby offering a comprehensive assessment of overall performance. Additionally, different types of feature selection are experimented. Factors used in machine learning models are either using all the independent variables or using significant factors from the stepwise method, and either considering or not considering exogenous factors of other products in the same cluster grouped by category, subcategory, or K-means method. The result shows that the series hybrid model of random forest and XGBoost outperformed others. Considering factors affecting sales, it is found that the promotion period factor was the most important, followed by discount percentage and price factors. This research provides analytics framework for sales prediction for retails using promotional pricing as a key demand driver.</p>","PeriodicalId":46686,"journal":{"name":"Journal of Revenue and Pricing Management","volume":"54 1","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2024-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Sales prediction hybrid models for retails using promotional pricing strategy as a key demand driver\",\"authors\":\"Naragain Phumchusri, Nichakan Phupaichitkun\",\"doi\":\"10.1057/s41272-024-00477-7\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The implementation of promotional pricing strategies constitutes a key component within the realm of retail revenue management. Nonetheless, the accurate prediction of sales in the presence of price discounts proves challenging due to the influence of various factors that contribute to demand uncertainty and high fluctuations. This study aims to find the most suitable prediction models for retail product unit sales while comprehensively accounting for the complex impacts of contributing factors. The dataset, sourced from a case study of a retail company, spans the temporal interval from January 2020 to December 2022. The predictive models, encompassing linear regression, random forest, XGBoost, artificial neural networks, and hybrid machine-learning models, are systematically developed. Then, the identification of the most suitable model is facilitated through the computation and comparative analysis of the Mean Absolute Percentage Error, with due consideration given to the weighting by the respective product’s revenue, thereby offering a comprehensive assessment of overall performance. Additionally, different types of feature selection are experimented. Factors used in machine learning models are either using all the independent variables or using significant factors from the stepwise method, and either considering or not considering exogenous factors of other products in the same cluster grouped by category, subcategory, or K-means method. The result shows that the series hybrid model of random forest and XGBoost outperformed others. Considering factors affecting sales, it is found that the promotion period factor was the most important, followed by discount percentage and price factors. This research provides analytics framework for sales prediction for retails using promotional pricing as a key demand driver.</p>\",\"PeriodicalId\":46686,\"journal\":{\"name\":\"Journal of Revenue and Pricing Management\",\"volume\":\"54 1\",\"pages\":\"\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2024-04-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Revenue and Pricing Management\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1057/s41272-024-00477-7\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Revenue and Pricing Management","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1057/s41272-024-00477-7","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
Sales prediction hybrid models for retails using promotional pricing strategy as a key demand driver
The implementation of promotional pricing strategies constitutes a key component within the realm of retail revenue management. Nonetheless, the accurate prediction of sales in the presence of price discounts proves challenging due to the influence of various factors that contribute to demand uncertainty and high fluctuations. This study aims to find the most suitable prediction models for retail product unit sales while comprehensively accounting for the complex impacts of contributing factors. The dataset, sourced from a case study of a retail company, spans the temporal interval from January 2020 to December 2022. The predictive models, encompassing linear regression, random forest, XGBoost, artificial neural networks, and hybrid machine-learning models, are systematically developed. Then, the identification of the most suitable model is facilitated through the computation and comparative analysis of the Mean Absolute Percentage Error, with due consideration given to the weighting by the respective product’s revenue, thereby offering a comprehensive assessment of overall performance. Additionally, different types of feature selection are experimented. Factors used in machine learning models are either using all the independent variables or using significant factors from the stepwise method, and either considering or not considering exogenous factors of other products in the same cluster grouped by category, subcategory, or K-means method. The result shows that the series hybrid model of random forest and XGBoost outperformed others. Considering factors affecting sales, it is found that the promotion period factor was the most important, followed by discount percentage and price factors. This research provides analytics framework for sales prediction for retails using promotional pricing as a key demand driver.
期刊介绍:
The?Journal of Revenue and Pricing Management?serves the community of researchers and practitioners dedicated to improving understanding through insight and real life situations. Each article emphasizes meaningful answers to problems whether cutting edge science or real solutions. The journal places an emphasis disseminating the best articles from the best minds and benchmarked businesses within the field of Revenue Management and Pricing.Revenue management (RM) also known as Yield Management (YM) is a management activity that marries the diverse disciplines of operations research/management science analytics economics human resource management software development marketing economics e-commerce consumer behaviour and consulting to manage demand for a firm's products or services with the goal of profit maximisation. From a practitioner standpoint RM encompasses a range of activities related to demand management including pricing segmentation capacity and inventory allocation demand modelling and business process management.Journal of Revenue and Pricing Management?aims to:formulate and disseminate a body of knowledge called 'RM and pricing' to practitioners educators researchers and students;provide an international forum for a wide range of practical theoretical and applied research in the fields of RM and pricing;represent a multi-disciplinary set of views on key and emerging issues in RM and pricing;include a cross-section of methodologies and viewpoints on research including quantitative and qualitative approaches case studies and empirical and theoretical studies;encourage greater understanding and linkage between the fields of study related to revenue management and pricing;to publish new and original ideas on research policy and managementencourage and engage with professional communities to adopt the Journal as the place of knowledge excellence i.e. INFORMS Revenue Management & Pricing section AGIFORS and Revenue Management Society and Revenue Management and Pricing International Ltd.Published six times a year?Journal of Revenue and Pricing Management?publishes a wide range of peer-reviewed practice papers research articles and professional briefings written by industry experts - including:Practice papers - addressing the issues facing practitioners in industry and consultancyApplied research papers - from leading institutions on all areas of research of interest to practitioners and the implications for practiceCase studies - focusing on the real-life challenges and problems faced by major corporations how they were approached and what was learnedModels and theories - practical models and theories which are being used in revenue managementThoughts - assessment of the key issues new trends and future ideas by leading experts and practitionersApprentice - the publication of tomorrows ideas by students of todayBook/conference reviews - reviewing leading conferences and major new books on RM and pricingThe Journal is essential reading for senior professionals in private and public sector organisations and academic observers in universities and business schools - including:Pricing AnalystsRevenue ManagersHeads of Revenue ManagementHeads of Yield ManagementDirectors of PricingHeads of MarketingChief Operating OfficersCommercial DirectorsDirectors of SalesDirectors of OperationsHeads of ResearchPricing ConsultantsProfessorsLecturers