{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T03:41:22Z","timestamp":1781062882366,"version":"3.54.1"},"reference-count":31,"publisher":"Emerald","issue":"12","license":[{"start":{"date-parts":[[2020,1,23]],"date-time":"2020-01-23T00:00:00Z","timestamp":1579737600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["K"],"published-print":{"date-parts":[[2020,1,23]]},"abstract":"<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title>\n<jats:p>The purpose of this paper is to solve the problem of low accuracy in new product demand forecasting caused by the absence of historical data and inadequate consideration of influencing factors.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title>\n<jats:p>A hybrid new product demand forecasting model combining clustering analysis and deep learning is proposed. Based on the product similarity measurement, the weight of product similarity attributes is realized by using the method of fuzzy clustering-rough set, which provides a basis for the acquisition and collation of historical sales data of similar products and the determination of product similarity. Then the prediction error of Bass model is adjusted based on similarity through a long short-term memory neural network model, where the influencing factors such as product differentiation, seasonality and sales time on demand forecasting are embedded. An empirical example is given to verify the validity and feasibility of the model.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Findings<\/jats:title>\n<jats:p>The results emphasize the importance of considering short-term impacts when forecasting new product demand. The authors show that useful information can be mined from similar products in demand forecasting, where the seasonality, product selling cycles and sales dependencies have significant impacts on the new product demand. In addition, they find that even in the peak season of demand, if the selling period has nearly passed the growth cycle, the Bass model may overestimate the product demand, which may mislead the operational decisions if it is ignored.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title>\n<jats:p>This study is valuable for showing that with the incorporation of the evaluation method on product similarity, the forecasting model proposed in this paper achieves a higher accuracy in forecasting new product sales.<\/jats:p>\n<\/jats:sec>","DOI":"10.1108\/k-10-2019-0688","type":"journal-article","created":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T10:11:41Z","timestamp":1580811101000},"page":"3099-3118","source":"Crossref","is-referenced-by-count":18,"title":["A hybrid method for forecasting new product sales based on fuzzy clustering and deep learning"],"prefix":"10.1108","volume":"49","author":[{"given":"Peng","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guowei","family":"Dou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangliang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","reference":[{"issue":"3","key":"key2020111314464374800_ref001","first-page":"116","article-title":"An epsilon constraint method for selecting indicators for use in neural networks for stock market forecasting","volume":"52","year":"2014","journal-title":"INFOR: Information Systems and Operational Research"},{"issue":"1","key":"key2020111314464374800_ref002","first-page":"255","article-title":"Characterization of demand for short life-cycle technology products","volume":"203","year":"2010","journal-title":"Annals of Operations Research"},{"issue":"5","key":"key2020111314464374800_ref003","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1287\/mnsc.15.5.215","article-title":"A new product growth for model consumer durables","volume":"15","year":"1969","journal-title":"Management Science"},{"issue":"3","key":"key2020111314464374800_ref004","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/0304-4076(86)90063-1","article-title":"Generalized autoregressive conditional heteroskedasticity","volume":"31","year":"1986","journal-title":"Journal of Econometrics"},{"key":"key2020111314464374800_ref005","volume-title":"Time Series Analysis, Control, and Forecasting","year":"1976"},{"issue":"2","key":"key2020111314464374800_ref006","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1016\/j.ijpe.2010.07.022","article-title":"Manufacturing intelligence for semiconductor demand forecast based on technology diffusion and product life cycle","volume":"128","year":"2010","journal-title":"International Journal of Production Economics"},{"issue":"4","key":"key2020111314464374800_ref007","doi-asserted-by":"crossref","first-page":"987","DOI":"10.2307\/1912773","article-title":"Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation","volume":"50","year":"1982","journal-title":"Econometrica"},{"key":"key2020111314464374800_ref008","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.jbusres.2017.01.010","article-title":"Product sales forecasting using online reviews and historical sales data: a method combining the bass model and sentiment analysis","volume":"74","year":"2017","journal-title":"Journal of Business Research"},{"issue":"1","key":"key2020111314464374800_ref009","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1287\/opre.44.1.87","article-title":"Reducing the cost of demand uncertainty through accurate response to early sales","volume":"44","year":"1996","journal-title":"Operations Research"},{"key":"key2020111314464374800_ref010","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1016\/j.eswa.2017.05.024","article-title":"Volatility of main metals forecasted by a hybrid ANN-GARCH model with regressors","volume":"84","year":"2017","journal-title":"Expert Systems with Applications"},{"issue":"8","key":"key2020111314464374800_ref011","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","year":"1997","journal-title":"Neural Computation"},{"issue":"5","key":"key2020111314464374800_ref012","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.patrec.2005.09.004","article-title":"Information-preserving hybrid data reduction based on fuzzy-rough techniques","volume":"27","year":"2006","journal-title":"Pattern Recognition Letters"},{"issue":"1","key":"key2020111314464374800_ref030","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1287\/mksc.10.1.83","article-title":"Innovation diffusion in the presence of supply restrictions","volume":"10","year":"1991","journal-title":"Marketing Science"},{"issue":"2","key":"key2020111314464374800_ref013","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ijmachtools.2005.05.003","article-title":"Fuzzy similarity-based rough set method for case-based reasoning and its application in tool selection","volume":"46","year":"2006","journal-title":"International Journal of Machine Tools and Manufacture"},{"issue":"10","key":"key2020111314464374800_ref014","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1287\/mnsc.1120.1529","article-title":"A generalized Norton\u2013Bass model for multigeneration diffusion","volume":"58","year":"2012","journal-title":"Management Science"},{"issue":"3","key":"key2020111314464374800_ref015","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/S0040-1625(97)00102-9","article-title":"Product growth models for medium-term forecasting of short life cycle products","volume":"57","year":"1998","journal-title":"Technological Forecasting and Social Change"},{"issue":"1","key":"key2020111314464374800_ref017","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/S0165-0114(00)00062-2","article-title":"An optimal algorithm for computing the max\u2013min transitive closure of a fuzzy similarity matrix","volume":"123","year":"2001","journal-title":"Fuzzy Sets and Systems"},{"key":"key2020111314464374800_ref016","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.techfore.2013.08.020","article-title":"Pre-launch new product demand forecasting using the bass model: a statistical and machine learning-based approach","volume":"86","year":"2014","journal-title":"Technological Forecasting and Social Change"},{"key":"key2020111314464374800_ref018","unstructured":"Morgan, J.P, and Reuter (1996), \u201cRisk metrics technical document\u201d, available at: www.jpmorgan.com"},{"issue":"9","key":"key2020111314464374800_ref019","doi-asserted-by":"crossref","first-page":"1069","DOI":"10.1287\/mnsc.33.9.1069","article-title":"A diffusion theory model of adoption and substitution for successive generations of high-technology products","volume":"33","year":"1987","journal-title":"Management Science"},{"issue":"5","key":"key2020111314464374800_ref020","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/BF01001956","article-title":"Rough sets","volume":"11","year":"1982","journal-title":"International Journal of Computer and Information Sciences"},{"issue":"7","key":"key2020111314464374800_ref031","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1080\/019697298125470","article-title":"Rough set theory and its applications to data analysis","volume":"29","year":"1998","journal-title":"Cybernetics & Systems"},{"issue":"1","key":"key2020111314464374800_ref021","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/S0019-9958(69)90591-9","article-title":"A new approach to clustering","volume":"15","year":"1969","journal-title":"Information and Control"},{"key":"key2020111314464374800_ref022","volume-title":"Product Lifecycle Management","year":"2008"},{"issue":"3","key":"key2020111314464374800_ref023","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/S0165-0114(03)00124-6","article-title":"Rough set analysis of a general type of fuzzy data using transitive aggregations of fuzzy similarity relations","volume":"139","year":"2003","journal-title":"Fuzzy Sets and Systems"},{"issue":"3","key":"key2020111314464374800_ref024","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1108\/03684921311323626","article-title":"A comparative study of hybrid machine learning techniques for customer lifetime value prediction","volume":"42","year":"2013","journal-title":"Kybernetes"},{"issue":"4","key":"key2020111314464374800_ref025","doi-asserted-by":"crossref","first-page":"8496","DOI":"10.1016\/j.eswa.2008.10.078","article-title":"Quadratic-interval bass model for new product sales diffusion","volume":"36","year":"2009","journal-title":"Expert Systems with Applications"},{"issue":"10","key":"key2020111314464374800_ref026","doi-asserted-by":"crossref","first-page":"12613","DOI":"10.1016\/j.eswa.2009.05.018","article-title":"Modified diffusion model with multiple products using a hybrid GA approach","volume":"36","year":"2009","journal-title":"Expert Systems with Applications"},{"issue":"7","key":"key2020111314464374800_ref027","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1108\/K-10-2013-0218","article-title":"Two-stage credit rating prediction using machine learning techniques","volume":"43","year":"2014","journal-title":"Kybernetes"},{"issue":"3","key":"key2020111314464374800_ref028","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.ejor.2010.09.005","article-title":"Competitive diffusion process of repurchased products in knowledgeable manufacturing","volume":"208","year":"2011","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"key2020111314464374800_ref029","doi-asserted-by":"crossref","first-page":"6580","DOI":"10.1016\/j.eswa.2008.07.064","article-title":"Forecasting box office revenue of movies with BP neural network","volume":"36","year":"2009","journal-title":"Expert Systems with Applications"}],"container-title":["Kybernetes"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/K-10-2019-0688\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/K-10-2019-0688\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T21:50:39Z","timestamp":1753393839000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/k\/article\/49\/12\/3099-3118\/457239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,23]]},"references-count":31,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,1,23]]}},"alternative-id":["10.1108\/K-10-2019-0688"],"URL":"https:\/\/doi.org\/10.1108\/k-10-2019-0688","relation":{},"ISSN":["0368-492X","0368-492X"],"issn-type":[{"value":"0368-492X","type":"print"},{"value":"0368-492X","type":"print"}],"subject":[],"published":{"date-parts":[[2020,1,23]]}}}