CN111815348A - Regional commodity production planning method based on commodity similarity clustering of stores - Google Patents

Regional commodity production planning method based on commodity similarity clustering of stores Download PDF

Info

Publication number
CN111815348A
CN111815348A CN202010467295.9A CN202010467295A CN111815348A CN 111815348 A CN111815348 A CN 111815348A CN 202010467295 A CN202010467295 A CN 202010467295A CN 111815348 A CN111815348 A CN 111815348A
Authority
CN
China
Prior art keywords
class
distance
commodity
stores
store
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010467295.9A
Other languages
Chinese (zh)
Inventor
王一君
陈灿
黄国安
吴珊珊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Lanzhong Data Technology Co ltd
Original Assignee
Hangzhou Lanzhong Data Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Lanzhong Data Technology Co ltd filed Critical Hangzhou Lanzhong Data Technology Co ltd
Priority to CN202010467295.9A priority Critical patent/CN111815348A/en
Publication of CN111815348A publication Critical patent/CN111815348A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a regional commodity production planning method based on commodity similarity clustering of stores. The invention specifically comprises the following steps: firstly, calculating a similarity matrix of each commodity on time sequence periodicity according to daily historical sales record data of all commodities of each store in the region; then calculating the variable quantity of commodity sales under different states according to external factors to obtain a sensitivity degree distance matrix among commodities; and clustering the commodities at the store level by combining the time sequence period similarity and the sensitivity degree distance matrix based on a clustering algorithm, selecting the optimal K types according to the elbow rule and the contour coefficient, predicting the future sales at the clustered level, and summarizing the K types of requirements to provide a production plan of the region. The method is beneficial to reducing the loss of goods shortage and overstock damage reporting risk, and plays an important role in improving the precision of regional production plans.

Description

Regional commodity production planning method based on commodity similarity clustering of stores
Technical Field
The invention belongs to the technical field of information, and particularly relates to a regional commodity production planning method based on commodity similarity clustering of stores.
Background
With the development of computer technology, computer networks and management systems are applied to almost every aspect of retail business, and factory production of areas is important to retail business machines. In the production plan of regional commodities, enterprises relate to different sales conditions of various stores, different external factor change degrees and different commodity production periods, and the store owners have different degrees of grasp on commodities, so that optimal prediction and decision are difficult to make on the production plan of regional commodities by decision makers. The production planning quantity of the area is given by two modes of always estimating the total quantity of the whole area and summarizing the total quantity to the area after the demand is proposed by depending on the experience of each store leader in many industries, but because the external change degrees of store commodities are different, the store leader levels are different, and a good production plan is difficult to make; therefore, it is a better way to aggregate similar stores and then predict sales across the aggregated categories and then give a production plan for the universe of the area.
In recent years, more and more industries pay attention to the importance of regional production prediction, most of industry prediction methods are based on a single-store single-product moving average model and then are adjusted according to business experiences of decision makers, but the phenomena of demand loss, commodity backlog loss and the like caused by inaccurate prediction exist. Therefore, the invention provides a regional commodity production planning method based on commodity similarity clustering of stores aiming at the situation, so as to guide enterprises to make more reasonable decisions of regional commodity production planning.
Disclosure of Invention
The invention aims to overcome the defects in the existing regional commodity production plan, and provides a regional commodity production plan method based on commodity similarity clustering of stores.
The invention comprises the following steps:
step 1: firstly, acquiring a transaction detail data set D of all store commodities in a historical designated time period, removing activity information and holiday information in the transaction detail data set D, and then counting according to day granularity to obtain a daily sales number set S of each store commodity;
step 2: based on the daily sales number set S of the commodities, calculating to obtain a time demand pattern T of each commodity on the periodicity:
Figure BDA0002513070280000021
Figure BDA0002513070280000022
wherein the content of the first and second substances,
Figure BDA0002513070280000023
average sales of the goods in week i, niRepresents the number of days of the inner perimeter i of the specified time period; d is an element of [1, n ]i]；
And step 3: according to a daily sales data set S and a weather factor data set X in a specified time period, taking the weather factor data set X as a model input X and the daily sales data set as a model output y, and training a linear regression model; then based on the change of each external weather factor data set X, obtaining a return coefficient, namely a change rate matrix E of daily sales;
and 4, step 4: based on the historical store daily sales data set S, calculating the time demand pattern distance between the commodity stores and sales data in a month close to the daily sales data set S, wherein the formula is as follows:
Figure BDA0002513070280000024
where i, j represent two different stores, Ti kA k-th element in the time demand pattern T representing store i;
and 5: based on the change rate matrix E of each commodity of each store, calculating to obtain the change rate distance of the external factors between the levels of each store, wherein the formula is as follows:
Figure BDA0002513070280000025
where i, j represent two different stores,
Figure BDA0002513070280000026
the kth element in the external factor change rate matrix E of the store i is represented;
step 6: distance Dis based on time demand patternsTAnd rate of change distance of external factors DisEAnd calculating the distance calculation method of the commodity at the store level, wherein the formula is as follows:
DIS(i，j)＝DisT(i，j)+DisE(i，j) (5)
DisT(i, j) represents the distance of store i, j in the time demand mode, DisE(i, j) represents the distance between stores i, j in terms of the rate of change of the external factor, DIS (i, j) represents the overall distance between stores i, j;
and 7: clustering similar stores according to a defined distance formula (5) among stores;
the similar stores are defined distances among stores;
and 8: obtaining an optimal class evaluation Score according to the minimum intra-class distance and the profile coefficient, and selecting an optimal classification number k according to the optimal class evaluation Score;
and step 9: after obtaining the optimal category number k according to the Score, summarizing sales in the category class;
step 10: predicting future sales y using ARIMA modelt；
Step 11: future sales for each class ytAnd summarizing to obtain the total predicted demand, namely the commodity production plan of the area.
Further, the clustering in step 7 adopts k-means clustering, and is implemented as follows:
inputting:
data set
Figure BDA0002513070280000031
And (3) outputting:
class center point
Figure BDA0002513070280000032
Labels C of points
Initialization:
randomly selecting k center points mu from the data set S1，…，μk
Figure BDA0002513070280000033
Firstly, initializing and randomly selecting k class center points, and for each sample s(i)Divide it into a distance mujThe most recent class label is c(j)According to c(j)Updating the center point μ for each categoryjUntil the class center does not change or the amount of change is less than a certain threshold value; and obtaining c, namely the class of each store and similar stores in the class.
Further, step 8 is specifically implemented as follows:
intra-class distance SSE:
Figure BDA0002513070280000041
selecting the number k of classes by selecting a mode of minimizing the overall distance;
contour coefficient SC:
Figure BDA0002513070280000042
a (i) is the average distance from the sample i to other samples in the class, b (i) is the average distance from the sample i to all samples in other classes, and the number of class centers k with smaller class distance and larger class distance is selected;
optimal class assessment Score:
Figure BDA0002513070280000043
and (3) combining the intra-class distance and the contour coefficient, and enabling the number of k to be larger when the intra-class distance is smaller and the inter-class distance is larger within the range of reasonable center number.
Further, after obtaining the optimal category number k according to the Score in step 9, the sales volume is summarized in the category class to obtain summarized sales data, which is specifically implemented as follows:
Figure BDA0002513070280000044
will belong to c(k)Store sample sales s of this type(i)Performing a summary;
further, the prediction of future sales by using the ARIMA model in step 10 is specifically realized as follows:
taking the aggregated sales data X as model input X:
Figure BDA0002513070280000045
μ is a constant term, etIs an error term, γiIs the autocorrelation coefficient, θiIs the error term coefficient.
The invention has the beneficial effects that:
according to the method, the similarity of the commodities at the store level is calculated according to the daily sales data and the sensitivity of the commodities, and the regional production plan is predicted according to the ARIMA model, so that a scientific and referable prediction result is provided for the region, the decision of the production plan of enterprises and the region is facilitated, the inventory condition is managed more reasonably, and the method plays an important role in reducing the stock shortage loss and the overstock damage risk and improving the regional production plan accuracy.
Drawings
Fig. 1 is a detailed flow chart of the method employed by the embodiment of the present invention.
FIG. 2 is a graph showing the results of the method according to the present invention.
Detailed Description
The objects and effects of the present invention will become more apparent from the following detailed description of the present invention when taken in conjunction with the accompanying drawings and tables. According to the method, the actual situation is considered, according to the historical sales data of the stores, the time sequence mode of the commodities and the distance matrix of the sensitivity degree of external factors are adopted, the optimal class center K number is selected by using the intra-class distance and the contour coefficient, the K mean algorithm is used for clustering the commodities at the store level, the future sales volume is predicted according to the ARIMA model, and the production plan decision of the regional commodities is realized.
A regional commodity production planning method based on commodity similarity clustering of stores.
The invention comprises the following steps:
step 1: firstly, acquiring a transaction detail data set D of all store commodities in a historical designated time period, removing activity information and holiday information in the transaction detail data set D, and then counting according to day granularity to obtain a daily sales number set S of each store commodity;
step 2: based on the daily sales number set S of the commodities, calculating to obtain a time demand pattern T of each commodity on the periodicity:
Figure BDA0002513070280000051
Figure BDA0002513070280000052
wherein the content of the first and second substances,
Figure BDA0002513070280000053
average sales of the goods in week i, niRepresents the number of days of the inner perimeter i of the specified time period; d is an element of [1, n ]i]；
And step 3: according to a daily sales data set S and a weather factor data set X in a specified time period, taking the weather factor data set X as a model input X and the daily sales data set as a model output y, and training a linear regression model; then based on the change of each external weather factor data set X, obtaining a return coefficient, namely a change rate matrix E of daily sales;
and 4, step 4: based on the historical store daily sales data set S, calculating the time demand pattern distance between the commodity stores and sales data in a month close to the daily sales data set S, wherein the formula is as follows:
Figure BDA0002513070280000061
where i, j represent two different stores, Ti kA k-th element in the time demand pattern T representing store i;
and 5: based on the change rate matrix E of each commodity of each store, calculating to obtain the change rate distance of the external factors between the levels of each store, wherein the formula is as follows:
Figure BDA0002513070280000062
where i, j represent two different stores,
Figure BDA0002513070280000063
the kth element in the external factor change rate matrix E of the store i is represented;
step 6: distance Dis based on time demand patternsTAnd rate of change distance of external factors DisEAnd calculating the distance calculation method of the commodity at the store level, wherein the formula is as follows:
DiS(i，j)＝DisT(i，j)+DisE(i，j) (5)
DisT(i, j) represents the distance of store i, j in the time demand mode, DisE(i, j) represents the distance between stores i, j in terms of the rate of change of the external factor, DiS (i, j) represents the overall distance between stores i, j;
and 7: clustering similar stores according to a defined distance formula (5) among stores;
the similar stores are defined distances among stores;
and 8: obtaining an optimal class evaluation Score according to the minimum intra-class distance and the profile coefficient, and selecting an optimal classification number k according to the optimal class evaluation Score;
and step 9: after obtaining the optimal category number k according to the Score, summarizing sales in the category class;
step 10: predicting future sales y using ARIMA modelt；
Step 11: future sales for each class ytAnd summarizing to obtain the total predicted demand, namely the commodity production plan of the area.
Further, the clustering in step 7 adopts k-means clustering, and is implemented as follows:
inputting:
data set
Figure BDA0002513070280000073
And (3) outputting:
class center point
Figure BDA0002513070280000074
Labels C of points
Initialization:
randomly selecting k center points mu from the data set S1，…，μk
Figure BDA0002513070280000071
Firstly, initializing and randomly selecting k class center points, and for each sample s(i)Divide it into a distance mujThe most recent class label is c(j)According to c(j)Updating the center point μ for each categoryjUntil the class center does not change or the amount of change is less than a certain threshold value; and obtaining c, namely the class of each store and similar stores in the class.
Further, step 8 is specifically implemented as follows:
intra-class distance SSE:
Figure BDA0002513070280000072
selecting the number k of classes by selecting a mode of minimizing the overall distance;
contour coefficient SC:
Figure BDA0002513070280000081
a (i) is the average distance from the sample i to other samples in the class, b (i) is the average distance from the sample i to all samples in other classes, and the number of class centers k with smaller class distance and larger class distance is selected;
optimal class assessment Score:
Figure BDA0002513070280000082
and (3) combining the intra-class distance and the contour coefficient, and enabling the number of k to be larger when the intra-class distance is smaller and the inter-class distance is larger within the range of reasonable center number.
Further, after obtaining the optimal category number k according to the Score in step 9, the sales volume is summarized in the category class to obtain summarized sales data, which is specifically implemented as follows:
Figure BDA0002513070280000083
will belong to c(k)Store sample sales s of this type(i)Performing a summary;
further, the prediction of future sales by using the ARIMA model in step 10 is specifically realized as follows:
taking the aggregated sales data X as model input X:
Figure BDA0002513070280000084
μ is a constant term, etIs an error term, γiIs the autocorrelation coefficient, θiIs the error term coefficient.
Fig. 2 is an example of the results of the regional production plan for the target commodity acquired in accordance with the present invention for the future 3 days, showing a comparison of predicted production volume and actual sales volume.
The present invention is not limited to the above-described embodiments, and those skilled in the art can implement the present invention in other various embodiments based on the disclosure of the present invention. Therefore, the design of the invention is within the scope of protection, with simple changes or modifications, based on the design structure and thought of the invention.

Claims (5)

1. A regional commodity production planning method based on commodity similarity clustering of stores is characterized by comprising the following steps:
step 1: firstly, acquiring a transaction detail data set D of all store commodities in a historical designated time period, removing activity information and holiday information in the transaction detail data set D, and then counting according to day granularity to obtain a daily sales number set S of each store commodity;
step 2: based on the daily sales number set S of the commodities, calculating to obtain a time demand pattern T of each commodity on the periodicity:
Figure FDA0002513070270000011
Figure FDA0002513070270000012
wherein the content of the first and second substances,
Figure FDA0002513070270000013
average sales of the goods in week i, niRepresents the number of days of the inner perimeter i of the specified time period; d is an element of [1, n ]i]；
And step 3: according to a daily sales data set S and a weather factor data set X in a specified time period, taking the weather factor data set X as a model input X and the daily sales data set as a model output y, and training a linear regression model; then based on the change of each external weather factor data set X, obtaining a return coefficient, namely a change rate matrix E of daily sales;
and 4, step 4: based on the historical store daily sales data set S, calculating the time demand pattern distance between the commodity stores and sales data in a month close to the daily sales data set S, wherein the formula is as follows:
Figure FDA0002513070270000014
where i, j represent two different stores, Ti kA k-th element in the time demand pattern T representing store i;
and 5: based on the change rate matrix E of each commodity of each store, calculating to obtain the change rate distance of the external factors between the levels of each store, wherein the formula is as follows:
Figure FDA0002513070270000015
where i, j represent two different stores,
Figure FDA0002513070270000016
the kth element in the external factor change rate matrix E of the store i is represented;
step 6: distance Dis based on time demand patternsTAnd rate of change distance of external factors DisEAnd calculating the distance calculation method of the commodity at the store level, wherein the formula is as follows:
DIS(i，j)＝DisT(i，j)+DisE(i，j)(5)
DisT(i, j) represents the distance of store i, j in the time demand mode, DisE(i, j) represents the distance between stores i, j in terms of the rate of change of the external factor, DIS (i, j) represents the overall distance between stores i, j;
and 7: clustering similar stores according to a defined distance formula (5) among stores;
the similar stores are defined distances among stores;
and 8: obtaining an optimal class evaluation Score according to the minimum intra-class distance and the profile coefficient, and selecting an optimal classification number k according to the optimal class evaluation Score;
and step 9: after obtaining the optimal category number k according to the Score, summarizing sales in the category class;
step 10: predicting future sales y using ARIMA modelt；
Step 11: future sales for each class ytAnd summarizing to obtain the total predicted demand, namely the commodity production plan of the area.
2. The regional commodity production planning method based on commodity similarity clustering of stores according to claim 1, characterized in that the clustering in step 7 adopts k-means clustering, and the following is realized:
inputting:
data set
Figure FDA0002513070270000021
And (3) outputting:
class center point
Figure FDA0002513070270000022
Labels C of points
Initialization:
randomly selecting k center points mu from the data set S1，…，μk
Figure FDA0002513070270000023
Figure FDA0002513070270000031
Firstly, initializing and randomly selecting k class center points, and for each sample s(i)Divide it into a distance mujThe most recent class label is c(j)According to c(j)Updating the center point μ for each categoryjUntil the class center does not change or the amount of change is less than a certain threshold value; and obtaining c, namely the class of each store and similar stores in the class.
3. The regional commodity production planning method based on commodity similarity clustering of stores according to claim 1 or 2, characterized in that step 8 is implemented as follows:
intra-class distance SSE:
Figure FDA0002513070270000032
selecting the number k of classes by selecting a mode of minimizing the overall distance;
contour coefficient SC:
Figure FDA0002513070270000033
a (i) is the average distance from the sample i to other samples in the class, b (i) is the average distance from the sample i to all samples in other classes, and the number of class centers k with smaller class distance and larger class distance is selected;
optimal class assessment Score:
Figure FDA0002513070270000034
and (3) combining the intra-class distance and the contour coefficient, and enabling the number of k to be larger when the intra-class distance is smaller and the inter-class distance is larger within the range of reasonable center number.
4. The regional commodity production planning method based on commodity similarity clustering of stores according to claim 3, characterized in that after obtaining the optimal category number k according to Score in step 9, sales are summarized in the category class to obtain summarized sales data, and the detailed implementation is as follows:
Figure FDA0002513070270000035
will belong to c(k)Store sample sales s of this type(i)A summary is made.
5. The regional commodity production planning method based on commodity similarity clustering of stores as claimed in claim 4, wherein the prediction of future sales using the ARIMA model in step 10 is implemented as follows:
taking the aggregated sales data X as model input X:
Figure FDA0002513070270000041
μ is a constant term, etIs an error term, γiIs the autocorrelation coefficient, θiIs the error term coefficient.
CN202010467295.9A 2020-05-28 2020-05-28 Regional commodity production planning method based on commodity similarity clustering of stores Pending CN111815348A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010467295.9A CN111815348A (en) 2020-05-28 2020-05-28 Regional commodity production planning method based on commodity similarity clustering of stores

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010467295.9A CN111815348A (en) 2020-05-28 2020-05-28 Regional commodity production planning method based on commodity similarity clustering of stores

Publications (1)

Publication Number Publication Date
CN111815348A true CN111815348A (en) 2020-10-23

Family

ID=72848100

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010467295.9A Pending CN111815348A (en) 2020-05-28 2020-05-28 Regional commodity production planning method based on commodity similarity clustering of stores

Country Status (1)

Country Link
CN (1) CN111815348A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113554335A (en) * 2021-08-02 2021-10-26 南京邮电大学 Production planning method based on big data
CN114186711A (en) * 2021-10-27 2022-03-15 中山大学 Industrial raw material consumption prediction method based on multitask time sequence learning
CN116739655A (en) * 2023-07-14 2023-09-12 上海朗晖慧科技术有限公司 Intelligent supply chain management method and system based on big data
CN117807412A (en) * 2024-03-01 2024-04-02 南京满鲜鲜冷链科技有限公司 Cargo damage prediction system based on vehicle-mounted sensor and big data

Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001084239A (en) * 1999-09-13 2001-03-30 Toshiba Corp Method for analyzing and predicting merchandise sales quantity, method for deciding merchandise order quantity and storage medium with program stored therein
US20020059096A1 (en) * 2000-11-13 2002-05-16 Toyoji Ikezawa Method and system for planning supply of commodities
JP2004334326A (en) * 2003-04-30 2004-11-25 Nri & Ncc Co Ltd System for predicting demand of merchandise and system for adjusting number of merchandise sold
CN101819668A (en) * 2010-04-27 2010-09-01 浙江大学 Sales predicting model based on product intrinsic life cycle character
US20140200992A1 (en) * 2013-01-14 2014-07-17 Oracle International Corporation Retail product lagged promotional effect prediction system
CN105556557A (en) * 2013-09-20 2016-05-04 日本电气株式会社 Shipment-volume prediction device, shipment-volume prediction method, recording medium, and shipment-volume prediction system
CN105956699A (en) * 2016-04-29 2016-09-21 连云港天马网络发展有限公司 Commodity classification and delivery and sales prediction method based on e-commerce sales data
CN107038190A (en) * 2016-10-28 2017-08-11 厦门大学 A kind of intelligent promotion plan modeling method applied to Taobao
CN109784979A (en) * 2018-12-19 2019-05-21 重庆邮电大学 A kind of supply chain needing forecasting method of big data driving
CN109784984A (en) * 2018-12-26 2019-05-21 广东工业大学 A kind of fresh shops's Intelligent Ordering System
US20190205806A1 (en) * 2017-12-28 2019-07-04 Walmart Apollo, Llc System and method for determining and implementing sales clusters for stores
US20190205823A1 (en) * 2017-12-28 2019-07-04 Walmart Apollo, Llc System and method for fine-tuning sales clusters for stores
CN109978597A (en) * 2019-01-22 2019-07-05 广东工业大学 A kind of Sales Volume of Commodity prediction technique under festivals or holidays effect
CN109978612A (en) * 2019-03-18 2019-07-05 北京工业大学 A kind of convenience store's Method for Sales Forecast method based on deep learning
CN110163669A (en) * 2019-05-09 2019-08-23 杭州览众数据科技有限公司 Needing forecasting method based on characteristic coefficient possibility predication and retail business business rule
CN110163427A (en) * 2019-05-09 2019-08-23 杭州览众数据科技有限公司 A kind of method of shops's inventory optimization
CN110189164A (en) * 2019-05-09 2019-08-30 杭州览众数据科技有限公司 Commodity-shops's suggested design based on comentropy measurement and feature stochastical sampling
CN110490670A (en) * 2019-08-27 2019-11-22 上海欧睿供应链管理有限公司 A kind of demand forecast system of adaptive merchandise sales rule
CN110751497A (en) * 2018-07-23 2020-02-04 北京京东尚科信息技术有限公司 Commodity replenishment method and device
CN111028016A (en) * 2019-12-12 2020-04-17 腾讯科技（深圳）有限公司 Sales data prediction method and device and related equipment

Patent Citations (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001084239A (en) * 1999-09-13 2001-03-30 Toshiba Corp Method for analyzing and predicting merchandise sales quantity, method for deciding merchandise order quantity and storage medium with program stored therein
US20020059096A1 (en) * 2000-11-13 2002-05-16 Toyoji Ikezawa Method and system for planning supply of commodities
JP2004334326A (en) * 2003-04-30 2004-11-25 Nri & Ncc Co Ltd System for predicting demand of merchandise and system for adjusting number of merchandise sold
CN101819668A (en) * 2010-04-27 2010-09-01 浙江大学 Sales predicting model based on product intrinsic life cycle character
US20140200992A1 (en) * 2013-01-14 2014-07-17 Oracle International Corporation Retail product lagged promotional effect prediction system
CN105556557A (en) * 2013-09-20 2016-05-04 日本电气株式会社 Shipment-volume prediction device, shipment-volume prediction method, recording medium, and shipment-volume prediction system
CN105956699A (en) * 2016-04-29 2016-09-21 连云港天马网络发展有限公司 Commodity classification and delivery and sales prediction method based on e-commerce sales data
CN107038190A (en) * 2016-10-28 2017-08-11 厦门大学 A kind of intelligent promotion plan modeling method applied to Taobao
US20190205806A1 (en) * 2017-12-28 2019-07-04 Walmart Apollo, Llc System and method for determining and implementing sales clusters for stores
US20190205823A1 (en) * 2017-12-28 2019-07-04 Walmart Apollo, Llc System and method for fine-tuning sales clusters for stores
CN110751497A (en) * 2018-07-23 2020-02-04 北京京东尚科信息技术有限公司 Commodity replenishment method and device
CN109784979A (en) * 2018-12-19 2019-05-21 重庆邮电大学 A kind of supply chain needing forecasting method of big data driving
CN109784984A (en) * 2018-12-26 2019-05-21 广东工业大学 A kind of fresh shops's Intelligent Ordering System
CN109978597A (en) * 2019-01-22 2019-07-05 广东工业大学 A kind of Sales Volume of Commodity prediction technique under festivals or holidays effect
CN109978612A (en) * 2019-03-18 2019-07-05 北京工业大学 A kind of convenience store's Method for Sales Forecast method based on deep learning
CN110163669A (en) * 2019-05-09 2019-08-23 杭州览众数据科技有限公司 Needing forecasting method based on characteristic coefficient possibility predication and retail business business rule
CN110163427A (en) * 2019-05-09 2019-08-23 杭州览众数据科技有限公司 A kind of method of shops's inventory optimization
CN110189164A (en) * 2019-05-09 2019-08-30 杭州览众数据科技有限公司 Commodity-shops's suggested design based on comentropy measurement and feature stochastical sampling
CN110490670A (en) * 2019-08-27 2019-11-22 上海欧睿供应链管理有限公司 A kind of demand forecast system of adaptive merchandise sales rule
CN111028016A (en) * 2019-12-12 2020-04-17 腾讯科技（深圳）有限公司 Sales data prediction method and device and related equipment

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113554335A (en) * 2021-08-02 2021-10-26 南京邮电大学 Production planning method based on big data
CN114186711A (en) * 2021-10-27 2022-03-15 中山大学 Industrial raw material consumption prediction method based on multitask time sequence learning
CN116739655A (en) * 2023-07-14 2023-09-12 上海朗晖慧科技术有限公司 Intelligent supply chain management method and system based on big data
CN116739655B (en) * 2023-07-14 2024-04-02 上海朗晖慧科技术有限公司 Intelligent supply chain management method and system based on big data
CN117807412A (en) * 2024-03-01 2024-04-02 南京满鲜鲜冷链科技有限公司 Cargo damage prediction system based on vehicle-mounted sensor and big data
CN117807412B (en) * 2024-03-01 2024-04-30 南京满鲜鲜冷链科技有限公司 Cargo damage prediction system based on vehicle-mounted sensor and big data

Similar Documents

Publication Publication Date Title
CN111815348A (en) Regional commodity production planning method based on commodity similarity clustering of stores
US8631040B2 (en) Computer-implemented systems and methods for flexible definition of time intervals
US7584116B2 (en) Monitoring a demand forecasting process
US7702518B2 (en) Method for assigning retail units to economic markets
CN113553540A (en) Commodity sales prediction method
Mahoney The adoption of the multidivisional form of organization: A contingency model
JP2021535451A (en) Optimization of demand forecast parameters
CN111178624A (en) Method for predicting new product demand
CN108389069A (en) Top-tier customer recognition methods based on random forest and logistic regression and device
CN114118636B (en) Automobile spare part demand prediction system based on multi-model optimization
US20140214492A1 (en) Systems and methods for price point analysis
CN108364191A (en) Top-tier customer Optimum Identification Method and device based on random forest and logistic regression
CN116739217A (en) Retail management method and system based on supply chain big data platform
CN116579804A (en) Holiday commodity sales prediction method, holiday commodity sales prediction device and computer storage medium
JP4386973B2 (en) Hierarchical prediction model construction apparatus and method
US11348146B2 (en) Item-specific value optimization tool
Suteja et al. Predicting the financial distress of Indonesian manufacturing companies: an application of the multinomial logit model
US20210142348A1 (en) Multi-layered system for heterogeneous pricing decisions by continuously learning market and hotel dynamics
US20140379422A1 (en) Inventory pricing based on price elasticity demand from movement trends
Rahman et al. A Bayesian approach to forecast intermittent demand for seasonal products
CN114444934A (en) Enterprise sales periodic evaluation algorithm and tool application thereof
Kabanova et al. ABC-XYZ inventory analysis accounting for change points
CN114219630A (en) Service risk prediction method, device, equipment and medium
JP2001243401A (en) Order receipt prediction system
US20140214493A1 (en) Systems and methods for waterfall adjustment analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination