MétaCan
Menu
← Back to cohort
Record W6939296420 · doi:10.60662/wb7m-xm85

Méthodologie de prévision des ventes B2B avec une demande intermittente

2023· article· fr· W6939296420 on OpenAlexaff

Bibliographic record

VenuePolyPublie (École Polytechnique de Montréal) · 2023
Typearticle
Languagefr
FieldAgricultural and Biological Sciences
TopicMycorrhizal Fungi and Plant Interactions
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsPerspective (graphical)Government (linguistics)Current (fluid)

Abstract

fetched live from OpenAlex

RÉSUMÉ: Dans le domaine de la prévision des ventes, le phénomène de demande intermittente pose un défi important pour la précision de la prévision. Une demande intermittente est sporadique et irrégulière. Les méthodes traditionnelles telles que les moyennes mobiles ou le lissage exponentiel ne sont pas capables de les prévoir. Le manque de données historiques et l'influence de facteurs externes peuvent rendre ces prévisions d’autant plus difficiles à faire. Pour faire face à ces défis, diverses méthodes avancées de prévision ont été proposées dans la littérature. Parmi ces méthodes, la méthode de Croston a été spécifiquement développée pour prévoir la demande intermittente. Les méthodes bayésiennes sont aussi connues à être efficaces pour modéliser l'incertitude et l'irrégularité de la demande. L'incorporation de données externes telles que les tendances de l'industrie ou du marché pourrait également améliorer la précision de la prévision. Cette étude vise à contribuer à cette littérature en étudiant à l’aide d’un cas industriel l'efficacité de ces différentes méthodes avancées à prévoir les ventes B2B pour les produits avec une demande intermittente. En outre, cette étude examine l'impact de l'incorporation de données externes sur la précision de la prévision. Nous proposons une application innovante pour améliorer la prévision en commençant par prédire quand la vente aura lieu. À cette fin, nous utilisons deux approches, soit une basée sur des modèles de classification et une basée sur l’analyse de séries temporelles des intervalles interdemande. Nous proposons également d'utiliser une approche d’agrégation / désagrégation temporelle afin de fournir une prévision plus précise de la demande. Les résultats fournissent des informations pertinentes pour les praticiens et les chercheurs dans le domaine de la prévision des ventes B2B, et peuvent contribuer au développement de stratégies de prévision plus robustes pour la demande intermittente. ABSTRACT: In the field of sales forecasting, the intermittent demand phenomenon poses a significant challenge for forecast accuracy. Intermittent demand is sporadic and irregular, and traditional methods such as moving averages or exponential smoothing are not capable of forecasting it. The lack of historical data and the influence of external factors can make these forecasts even more difficult to make. To address these challenges, various advanced forecasting methods have been proposed in the literature. Among these methods, the Croston method has been specifically developed to forecast intermittent demand. Bayesian methods are also known to be effective in modeling the uncertainty and irregularity of demand. The incorporation of external data such as industry or market trends could also improve forecast accuracy. This study aims to contribute to this literature by studying the effectiveness of these different advanced methods in forecasting B2B sales for products with intermittent demand using an industrial case. Furthermore, this study examines the impact of the incorporation of external data on forecast accuracy. We propose an innovative application to improve forecasting by first predicting when the sale will occur. To this end, we use two approaches, one based on classification models, and one based on analysis of interdemand time series intervals. We also propose using a temporal aggregation/disaggregation approach to provide a more accurate demand forecast. The results provide relevant information for practitioners and researchers in the field of B2B sales forecasting and can contribute to the development of more robust forecasting strategies for intermittent demand.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.014
Threshold uncertainty score0.029

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.006
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0010.000
Scholarly communication0.0020.001
Open science0.0020.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0070.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.030
GPT teacher head0.263
Teacher spread0.232 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same venuePolyPublie (École Polytechnique de Montréal)→Same topicMycorrhizal Fungi and Plant Interactions→French-language works237,207→