Abstract
The production decision of a large commodity or equipment manufacturing enterprise can be modeled as a newsvendor problem. Managers must determine the optimal production volume in advance to minimize the underage cost and the overage cost. However, the traditional newsvendor problem assumes the known demand distribution, which is not the case in practice. Data-driven approaches have become the hot research topic and opened up new avenues for such issues. Recent studies have considered demand-related features but have failed to address how to optimize production and inventory using informative textual reviews, not just numerical feature data. To address this issue, we propose a data-driven newsvendor model that leverages sentiment analysis on textual reviews using a deep learning model to solve the data-driven newsvendor problem by integrating estimation and optimization. Experiments on real data show that our proposed method reduces the average cost by approximately 14.18% compared to the most advanced deep neural network method, making it the best-performing method. Furthermore, our method is more suitable for situations where unit shortage costs are greater than unit overage costs. Finally, our method is robust in terms of sample size and can still obtain good results even with insufficient historical data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
Akhtar MS, Ekbal A, Cambria E (2020) How intense are you? Predicting intensities of emotions and sentiments using stacked ensemble [application notes]. IEEE Comput Intell Mag 15(1):64–75. https://doi.org/10.1109/MCI.2019.2954667
Akter S, Aziz MT (2016) Sentiment analysis on facebook group using lexicon based approach. Paper presented at the 2016 3rd international conference on electrical engineering and information communication technology (ICEEICT), 22–24 Sept. 2016
Alam MH, Ryu W-J, Lee S (2016) Joint multi-grain topic sentiment: modeling semantic aspects for online reviews. Inf Sci 339:206–223. https://doi.org/10.1016/j.ins.2016.01.013
Archak N, Ghose A, Ipeirotis PG (2011) Deriving the pricing power of product features by mining consumer reviews. Manag Sci 57(8):1485–1509. https://doi.org/10.1287/mnsc.1110.1370
Arrow KJ, Harris T, Marschak J (1951) Optimal inventory policy. Econometrica 19:250–272
Arunraj NS, Ahrens D (2015) A hybrid seasonal autoregressive integrated moving average and quantile regression for daily food sales forecasting. Int J Prod Econ 170:321–335. https://doi.org/10.1016/j.ijpe.2015.09.039
Bai X (2011) Predicting consumer sentiments from online text. Decis Support Syst 50(4):732–742. https://doi.org/10.1016/j.dss.2010.08.024
Ban GY, Rudin C (2019) The big Data newsvendor: practical insights from machine learning. Oper Res 67(1):90–108. https://doi.org/10.1287/opre.2018.1757
Bertsimas D, Thiele A (2005) A data-driven approach to newsvendor problems. Working paper, Massachusetts Institute of Technology, 51
Besbes O, Muharremoglu A (2013) On implications of demand censoring in the newsvendor problem. Manag Sci 59(6):1407–1424. https://doi.org/10.1287/mnsc.1120.1654
Bi JW, Han TY, Yao Y, Li H (2022a) Ranking hotels through multi-dimensional hotel information: a method considering travelers’ preferences and expectations. Inf Technol Tour 24(1):127–155. https://doi.org/10.1007/s40558-022-00223-y
Bi X, Adomavicius G, Li W, Qu A (2022b) Improving sales forecasting accuracy: a tensor factorization approach with demand awareness. Informs J Comput 34(3):1644–1660. https://doi.org/10.1287/ijoc.2021.1147
Cao Y, Shen Z-JM (2019) Quantile forecasting and data-driven inventory management under nonstationary demand. Oper Res Lett 47(6):465–472. https://doi.org/10.1016/j.orl.2019.08.008
Cao N, Ji S, Chiu DKW, He M, Sun X (2020) A deceptive review detection framework: combination of coarse and fine-grained features. Expert Syst Appl 156:113465. https://doi.org/10.1016/j.eswa.2020.113465
Chang Y-C, Ku C-H, Chen C-H (2020) Using deep learning and visual analytics to explore hotel reviews and responses. Tour Manag 80:104129. https://doi.org/10.1016/j.tourman.2020.104129
Chen Y, Xie J (2008) Online consumer review: Word-of-mouth as a new element of marketing communication mix. Manag Sci 54(3):477–491. https://doi.org/10.1287/mnsc.1070.0810
Chong AYL, Li B, Ngai EWT, Ch’ng E, Lee F (2016) Predicting online product sales via online reviews, sentiments, and promotion strategies: A big data architecture and neural network approach. Int J Oper Prod Manag 36(4):358–383. https://doi.org/10.1108/IJOPM-03-2015-0151
Dey A, Jenamani M, Thakkar JJ (2018) Senti-N-Gram: an n-gram lexicon for sentiment analysis. Expert Syst Appl 103:92–105. https://doi.org/10.1016/j.eswa.2018.03.004
Duan W, Gu B, Whinston AB (2008) Do online reviews matter?—an empirical investigation of panel data. Decis Support Syst 45(4):1007–1016. https://doi.org/10.1016/j.dss.2008.04.001
Elmachtoub AN, Grigas P (2022) Smart “predict, then optimize.” Manag Sci 68(1):9–26. https://doi.org/10.1287/mnsc.2020.3922
Fan Z-P, Che Y-J, Chen Z-Y (2017) Product sales forecasting using online reviews and historical sales data: a method combining the Bass model and sentiment analysis. J Bus Res 74:90–100. https://doi.org/10.1016/j.jbusres.2017.01.010
Fernández-Gavilanes M, Álvarez-López T, Juncal-Martínez J, Costa-Montenegro E, Javier González-Castaño F (2016) Unsupervised method for sentiment analysis in online texts. Expert Syst Appl 58:57–75. https://doi.org/10.1016/j.eswa.2016.03.031
He B, Dexter F, Macario A, Zenios S (2012) The timing of staffing decisions in hospital operating rooms: incorporating workload heterogeneity into the newsvendor problem. Manuf Serv Oper Manag 14(1):99–114. https://doi.org/10.1287/msom.1110.0350
Huber J, Müller S, Fleischmann M, Stuckenschmidt H (2019) A data-driven newsvendor problem: from data to decision. Eur J Oper Res 278(3):904–915. https://doi.org/10.1016/j.ejor.2019.04.043
Kang Y, Cai Z, Tan C-W, Huang Q, Liu H (2020) Natural language processing (NLP) in management research: a literature review. Journal of Management Analytics 7(2):139–172. https://doi.org/10.1080/23270012.2020.1756939
Keskin NB, Li Y, Song J-S (2022) Data-driven dynamic pricing and ordering with perishable inventory in a changing environment. Manag Sci 68(3):1938–1958. https://doi.org/10.1287/mnsc.2021.4011
Khorsand R, Rafiee M, Kayvanfar V (2020) Insights into TripAdvisor’s online reviews: the case of Tehran’s hotels. Tour Manag Perspect 34:100673. https://doi.org/10.1016/j.tmp.2020.100673
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. Paper presented at the 3rd international conference on learning representations, ICLR 2015
Kotelnikova A, Paschenko D, Bochenina K, Kotelnikov E (2022) Lexicon-based methods vs. BERT for text sentiment analysis. Paper presented at the analysis of images, social networks and texts, Cham, 2022
Ku L-W, Chen H-H (2007) Mining opinions from the Web: Beyond relevance retrieval. J Am Soc Inform Sci Technol 58(12):1838–1850. https://doi.org/10.1002/asi.20630
Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York
Kyparisis GJ, Koulamas C (2018) The price-setting newsvendor with nonlinear salvage revenue and shortage cost. Oper Res Lett 46(1):64–68. https://doi.org/10.1016/j.orl.2017.11.001
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444. https://doi.org/10.1038/nature14539
Levi R, Roundy RO, Shmoys DB (2007) Provably near-optimal sampling-based policies for stochastic inventory control models. Math Oper Res 32(4):821–839. https://doi.org/10.1287/moor.1070.0272
Lin S, Chen Y, Li Y, Shen ZJM (2021) Data-driven newsvendor problems regularized by a profit risk constraint. Prod Oper Manag. https://doi.org/10.1111/poms.13635
Liu Y, Bi J-W, Fan Z-P (2017a) Multi-class sentiment classification: the experimental comparisons of feature selection and machine learning algorithms. Expert Syst Appl 80:323–339. https://doi.org/10.1016/j.eswa.2017.03.042
Liu Y, Bi J-W, Fan Z-P (2017b) Ranking products through online reviews: a method based on sentiment analysis technique and intuitionistic fuzzy set theory. Inf Fus 36:149–161. https://doi.org/10.1016/j.inffus.2016.11.012
Liu Y, Bi JW, Fan ZP (2017c) A method for ranking products through online reviews based on sentiment classification and interval-valued intuitionistic fuzzy topsis. Int J Inf Technol Decis Mak 16(6):1497–1522. https://doi.org/10.1142/S021962201750033X
Liu Y, Jiang C, Zhao H (2018) Using contextual features and multi-view ensemble learning in product defect identification from online discussion forums. Decis Support Syst 105:1–12. https://doi.org/10.1016/j.dss.2017.10.009
Liu C, Letchford AN, Svetunkov I (2022) Newsvendor problems: an integrated method for estimation and optimisation. Eur J Oper Res 300(2):590–601. https://doi.org/10.1016/j.ejor.2021.08.013
Liyanage LH, Shanthikumar JG (2005) A practical inventory control policy using operational statistics. Oper Res Lett 33(4):341–348. https://doi.org/10.1016/j.orl.2004.08.003
Martinez-Torres MR, Toral SL (2019) A machine learning approach for the identification of the deceptive reviews in the hospitality sector using unique attributes and sentiment orientation. Tour Manag 75:393–403. https://doi.org/10.1016/j.tourman.2019.06.003
Mohamad Beigi O, Moattar MH (2021) Automatic construction of domain-specific sentiment lexicon for unsupervised domain adaptation and sentiment classification. Knowl Based Syst 213:106423. https://doi.org/10.1016/j.knosys.2020.106423
Moreno-Ortiz A, Fernández-Cruz J (2015) Identifying polarity in financial texts for sentiment analysis: a corpus-based approach. Procedia Soc Behav Sci 198:330–338. https://doi.org/10.1016/j.sbspro.2015.07.451
Moreo A, Romero M, Castro JL, Zurita JM (2012) Lexicon-based comments-oriented news sentiment analyzer system. Expert Syst Appl 39(10):9166–9180. https://doi.org/10.1016/j.eswa.2012.02.057
Najmi E, Hashmi K, Malik Z, Rezgui A, Khan HU (2015) CAPRA: a comprehensive approach to product ranking using customer reviews. Computing 97(8):843–867. https://doi.org/10.1007/s00607-015-0439-8
Oroojlooyjadid A, Snyder LV, Takáč M (2019) Applying deep learning to the newsvendor problem. IISE Trans 52(4):444–463. https://doi.org/10.1080/24725854.2019.1632502
Peng S, Cao L, Zhou Y, Ouyang Z, Yang A, Li X, Jia W, Yu S (2022) A survey on deep learning for textual emotion analysis in social networks. Digital Commun Netw 8(5):745–762. https://doi.org/10.1016/j.dcan.2021.10.003
Pirayesh Neghab D, Khayyati S, Karaesmen F (2022) An integrated data-driven method using deep learning for a newsvendor problem with unobservable features. Eur J Oper Res. https://doi.org/10.1016/j.ejor.2021.12.047
Qi M, Mak HY, Shen ZJM (2020) Data-driven research in retail operations—a review. Nav Res Logist 67(8):595–616. https://doi.org/10.1002/nav.21949
Qi M, Shi Y, Qi Y, Ma C, Yuan R, Wu D, Shen Z-JM (2023) A practical end-to-end inventory management model with deep learning. Manage Sci 69(2):759–773. https://doi.org/10.1287/mnsc.2022.4564
Székely GJ, Rizzo ML, Bakirov NK (2007) Measuring and testing dependence by correlation of distances. Ann Stat 35(6):2769–2794. https://doi.org/10.1214/009053607000000505
Vana PM, Lambrecht AM (2018) Online reviews: star ratings, position effects and purchase likelihood. Social Science Electronic Publishing, Rochester
Weichselbraun A, Gindl S, Scharl A (2011) Using games with a purpose and bootstrapping to create domain-specific sentiment lexicons. Paper presented at the proceedings of the 20th ACM international conference on Information and knowledge management, Glasgow, Scotland, UK. https://doi.org/10.1145/2063576.2063729
Wu H, Gu Y, Sun S, Gu X (2016) Aspect-based opinion summarization with convolutional neural networks. Paper presented at the 2016 international joint conference on neural networks (IJCNN), 24–29 July 2016
Ye Q, Law R, Gu B (2009) The impact of online user reviews on hotel room sales. Int J Hosp Manag 28(1):180–182. https://doi.org/10.1016/j.ijhm.2008.06.011
Zhang C, Tian YX, Fan LW (2020a) Improving the Bass model’s predictive power through online reviews, search traffic and macroeconomic data. Ann Oper Res 295(2):881–922. https://doi.org/10.1007/s10479-020-03716-3
Zhang C, Tian YX, Fan LW, Li YH (2020b) Customized ranking for products through online reviews: a method incorporating prospect theory with an improved VIKOR. Appl Intell 50(6):1725–1744. https://doi.org/10.1007/s10489-019-01577-3
Zhang C, Tian YX, Fan ZP, Liu Y, Fan LW (2020c) Product sales forecasting using macroeconomic indicators and online reviews: a method combining prospect theory and sentiment analysis. Soft Comput 24(9):6213–6226. https://doi.org/10.1007/s00500-018-03742-1
Zhang C, Tian YX, Fan ZP (2021) Forecasting sales using online review and search engine data: a method based on PCA–DSFOA–BPNN. Int J Forecast. https://doi.org/10.1016/j.ijforecast.2021.07.010
Zhang C, Tian YX, Fan ZP (2022) Forecasting the box offices of movies coming soon using social media analysis: a method based on improved Bass models. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.116241
Zhu XD, Ninh A, Zhao H, Liu ZM (2021) Demand forecasting with supply-chain information and machine learning: evidence in the pharmaceutical industry. Prod Oper Manag 30(9):3231–3252. https://doi.org/10.1111/poms.13426
Funding
This work was supported by the National Social Science Fund of China [Grant Number, 19BGL229].
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by CZ and Y-XT. The first draft of the manuscript was written by Y-XT, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interests
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, C., Tian, YX. Solving data-driven newsvendor problem with textual reviews through deep learning. Soft Comput 28, 4967–4986 (2024). https://doi.org/10.1007/s00500-023-09073-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-023-09073-0