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

New product demand prediction method

A technology for demand forecasting and new products, applied in forecasting, instruments, computing models, etc., can solve problems such as heterogeneous product differentiation, demand evolution, clustering and forecasting model mismatch, and achieve high accuracy.

Pending Publication Date: 2020-05-19
ZHEJIANG UNIV +1
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the problems and deficiencies in the prior art described above, in order to solve the problems of demand evolution, mismatch between clustering and forecasting models, and differentiation of heterogeneous products in the process of new product forecasting, the present invention proposes a method based on analogy Forecasting Framework, Changes in Synthetic Demand Distribution, Machine Learning Forecasting Methods for Category Consistency

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
  • New product demand prediction method
  • New product demand prediction method
  • New product demand prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] There are 10 new fruit products that are expected to go on sale on April 1, 2019, and the demand for April 1-7, 2019 needs to be forecasted. There are 100 products with historical sales records, then extract product attribute features for these 100 products

[0047] A i =(PL i ,BL i ,C i ,FP i ,FMCG i ,PT i ,PPi ), i∈[1,100]

[0048] where PL i ,BL i ,C i ,FP i ,FMCG i ,PT i ,PP i Indicates the price level, brand level, category, functional parameters, fast-moving consumer goods, packaging type, and origin of product i.

[0049] Extract the feature and demand matrix used for product i model training, assuming product i has t i Duration History

[0050]

[0051] where S j ,j∈[1,t i ] represents the historical demand of product i, element f j,* Represents the eigenvectors corresponding to each historical demand, where the demand is represented by sales.

[0052] Similarly, to extract the attribute features of new products

[0053] NA k =(PL k ,BL...

Embodiment 2

[0077] 5 new women's wear products are expected to go on sale on May 6, 2019, and the demand for May 6-12, 2019 needs to be forecasted. In this case, the demand is calculated by (sales and product launch time) / store sales time. There are currently 200 products with historical sales records, and the product attribute features are extracted from these 200 products

[0078] A i =(PL i ,BL i ,C i ,FP i ,FMCG i ,PT i ,PP i ,ST i , NS i ,NC i ), i∈[1,200]

[0079] A i The 10 fields inside represent the price level, brand level, category, functional parameters, fast moving consumer goods or not, packaging type, origin, style, size quantity, and color quantity of product i respectively.

[0080] Extract the feature and demand matrix used for product i model training, assuming product i has t i Duration History

[0081]

[0082] where S j ,j∈[1,t i ] represents the historical demand of product i, element f j,* Represents the eigenvector corresponding to each histor...

Embodiment 3

[0108] There are 3 new mobile phones that are expected to go on sale on April 15, 2019, and the demand for April 15-21, 2019 needs to be forecasted. In this case, actual sales are used to represent demand. There are 120 products with historical sales records, then extract product attribute features for these 120 products

[0109] A i =(PL i ,BL i ,C i ,FP i ,ZP i ,ST i ,SZ i ,NC i ,PZL i ), i∈[1,120]

[0110] A i The 10 fields inside represent the price level, brand level, category, function parameters, main screen size, style, size, color quantity, and configuration level of the same price of product i respectively.

[0111] Extract the features (all continuous values) and demand matrix used for product i model training, assuming that product i has t i Duration History

[0112]

[0113] where S j ,j∈[1,t i ] represents the historical demand of product i, element f j,* Represents the eigenvector corresponding to each historical demand.

[0114] Similarly, ...

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 relates to a new product demand prediction method, which is characterized by comprising the following steps of: calculating the correlation between historical demand quantity and characteristics of historical sold products, clustering the historical sold products according to a correlation vector, and classifying the new products into certain classes by a certain classification mechanism according to a classification vector; constructing a training set by using demanded quantity data of historical sold products in the same class, and selecting training data in the latest period of time to be trained by using a machine learning model; and respectively predicting the new products by using the corresponding classes, and combining the prediction values to obtain a final demand prediction value. By means of the new product demand prediction method, dynamic evolution of the product demand of the product from one month to two years in the future can be described, all-channel andall-link information under the big data background is fully utilized, an algorithm framework of machine learning can be well matched, and the predicted product demand has high accuracy compared witha traditional method.

Description

technical field [0001] The invention relates to the intersecting field of machine learning and supply chain management, in particular to a method for pattern learning and prediction of consumer demand. Background technique [0002] The development of the Internet, mobile marketing, and new retail has put forward higher requirements for merchants' demand perception, product planning, and supply chain response speed. In the field of new product planning, accurately predicting future demand and demand change trends will greatly shorten the response time of the supply chain and reduce production and inventory costs. How to effectively predict the future demand of new products has gradually become an important issue and difficult problem in product operation and management under the fast-paced business model change. Since new products do not have any historical data, traditional time series and machine learning models are not applicable. Developing an effective and feasible fore...

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
IPC IPC(8): G06Q10/04G06Q10/06G06N20/00
CPCG06Q10/04G06Q10/06315G06N20/00
Inventor 周伟华周云李泽宇钱仲文
Owner ZHEJIANG UNIV
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