Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Demand Forecasting Method Based on Likelihood Estimation of Characteristic Coefficients and Retail Business Rules

A technology of likelihood estimation and characteristic coefficient, applied in the field of supply chain automation management engineering, it can solve the problems of large deviation of the amount of advice and estimation, incomplete thinking of the calculation plan, business restrictions and business changes, etc., to achieve turnover increase and out of stock. rate reduction improvement, high industrial application performance and optimized performance, and the effect of improving time efficiency

Active Publication Date: 2021-07-27
杭州览众数据科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Most of the existing intelligent management platforms are general-purpose platforms, and the general-purpose solutions are not customized for the details of the enterprise's business. Enterprises are still required to control the terminal needs and deployment. The number of suggestions provided by the platform system also has large deviations in estimation, and the calculation plan is not comprehensive. Failure to deal with more business restrictions and business changes in terminal retail

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Demand Forecasting Method Based on Likelihood Estimation of Characteristic Coefficients and Retail Business Rules
  • A Demand Forecasting Method Based on Likelihood Estimation of Characteristic Coefficients and Retail Business Rules
  • A Demand Forecasting Method Based on Likelihood Estimation of Characteristic Coefficients and Retail Business Rules

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The purpose and effects of the present invention will become more apparent by describing the present invention in detail below in conjunction with the accompanying drawings.

[0037] Such as figure 1 As shown, the present invention considers a kind of demand prediction method based on feature coefficient likelihood estimation and retail industry business rule, it is characterized in that, comprises the following steps:

[0038] Step 1: Initialize the associated data of the retail terminal business process: store set I, single product set J, timeline t, week number Wt , inventory quantity SS at the beginning of the day, inventory quantity ES at the end of the day, arrival quantity D, actual sales volume X, forecast sales volume The number of containers displayed C, the number of weeks that can be ordered by the store O, and the number of days L between the logistics delivery and the store arrival are used in the single product arrival demand forecasting module; the int...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a demand prediction method based on characteristic coefficient likelihood estimation and retail business rules. Firstly, the invention first obtains store traffic and external factor data such as weather, temperature, holidays, etc., and uses a linear regression method to obtain an estimated amount of future turnover; Secondly, the characteristics of the week and the corresponding sales ratio of the week are constructed, and the stores are clustered after defining the similarity of the stores based on the Euclidean metric rule. By merging the weeks with similar sales ratios, the week group features are constructed; then, the weighted temperature and The average value of recent sales is added to the feature set, and the daily sales distribution is obtained by using the GLM model; finally, the daily delivery demand is calculated based on the store's display requirements, order restrictions and other rules to complete the retail demand forecast. The invention constructs model features based on business considerations, establishes a commodity demand model in the retail industry, and greatly improves the operating efficiency of retail stores.

Description

technical field [0001] The invention relates to the field of supply chain automation management engineering, specifically, a demand prediction method based on characteristic coefficient likelihood estimation and retail business rules serves terminal operation and management. Background technique [0002] In today's supply chain automation management engineering field, whether it is actual business practice or theoretical research, optimizing supply chain inventory to meet customer needs has always been one of the core businesses of enterprises, reducing inventory investment while ensuring retail shelves and distribution The center stocks just the right amount of merchandise. [0003] Most of the existing intelligent management platforms are general-purpose platforms, and the general-purpose solutions are not customized for the details of the enterprise's business. Enterprises are still required to control the terminal needs and deployment. The amount of suggestions provided ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q30/02G06F17/18
CPCG06F17/18G06Q30/0201G06Q30/0203
Inventor 王一君陈灿吴黎平吴珊珊
Owner 杭州览众数据科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com