A commercial size distribution evaluation method

Abstract

The present invention discloses a commercial size distribution evaluation method, which belongs to the field of commodity management technology. The commercial size distribution evaluation method includes counting the sales of SKUs; determining the "ideal ratio" of the size distribution that is as close as possible to the theoretical sales; inputting the inventory of SKUs and calculating various indicators; generating an indicator summary of SKUs; upgrading the SKU indicators to SPU indicators; calculating the size comprehensive value of SPU or SKU, and outputting the corresponding size comprehensive value. The size quality of the commodity is comprehensively and quickly evaluated by the size comprehensive value, so that the front-line operation and commodity personnel can quickly understand the distribution of the golden size of the commodity, and at the same time compare the degree of fit between the current inventory and the actual sales situation, so that the seller can quickly understand the size quantity and quality status of the current inventory. It has the advantages of rapid comprehensive evaluation of the size, prediction of inventory sales, and targeted replenishment, thereby achieving the purpose of improving work efficiency and quality and reducing labor costs.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce management, and in particular to a commercial size distribution evaluation method. Background Art

[0002] Electronic commerce management, referred to as e-commerce, is a new business operation model that is usually carried out in extensive commercial trade activities around the world in the open network environment of the Internet, based on browsers or server applications, in which buyers and sellers conduct various commercial activities without meeting each other, realizing consumers' online shopping, online transactions and online electronic payments between merchants, as well as various business activities, transaction interactions, financial activities and related comprehensive service activities.

[0003] At present, the e-commerce management system in the prior art is mainly used for commodity transactions. It is difficult to quickly understand the changes in commodity sizes or the impact of size quality on sales, and it is impossible to directly observe the degree of fit between the current commodity inventory and the actual sales situation, which easily leads to invalid inventory. It can be seen from the above that the existing e-commerce management system has the disadvantages of lack of rapid evaluation of commodity sizes and difficulty in observing the degree of fit between the current commodity inventory and the actual sales situation, thereby affecting the final sales results.

[0004] Therefore, it is necessary to provide a commercial size distribution evaluation method to solve the above problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, an embodiment of the present invention aims to provide a commercial size distribution evaluation method to solve the problems in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A commercial size distribution evaluation method comprises the following steps:

[0008] S1: Statistics on SKU sales;

[0009] S2: Determine the “ideal ratio”;

[0010] S3: Input the inventory of SKU and calculate various indicators, including size consistency, size efficiency, main size ratio, main size inventory ratio, main size total inventory and main size consistency ratio;

[0011] S4: Generate SKU indicator summary;

[0012] S5: Upgrade the SKU indicator to the SPU indicator;

[0013] S6: Calculate the size comprehensive value of the SPU or SKU, and output the corresponding size comprehensive value.

[0014] As a further solution of the present invention, determining the "ideal ratio" in S2 includes the following steps:

[0015] 1) Count the sales size distribution of each SKU during the selected sales cycle, arrange them in order from small to large according to the number of sizes, and name the ratio as the sales statistical ratio; consult the brand to count the whole-hand ratio of each SKU when the factory places an order; obtain the sales ratio of the benchmark product through the data of competing products;

[0016] 2) Export the results of the above data, generate an intermediate file, analyze the rationality of the above ratios, find out the reasons for the obviously abnormal ratios, and manually modify the parts that need to be modified;

[0017] 3) Cluster analysis is performed on the above ratios to find the same pattern and determine the final "ideal ratio".

[0018] As a further solution of the present invention, the uniformity is a Boolean variable, which is defined as: if all size stocks under the SKU are above the safety stock, the uniformity is 1, otherwise, it is assigned a value of 0, that is, determining whether all sizes in the size master file are in stock.

[0019] As a further solution of the present invention, the size efficiency is a Float variable, that is, the size in the intersection of sales and inventory, with a value range of [0, 100%]. For each SKU, the chi-square value of the current inventory size distribution and the "ideal ratio" is calculated. The calculation formula is as follows:

[0020] is the goodness of fit; where r refers to the number of sizes under the SKU; n refers to the number of stocks under the SKU; p k It refers to the proportion of size k in the ideal proportion; np k It refers to the ideal inventory number of the product in theory according to the ideal ratio; n k It refers to the inventory number corresponding to size k in the actual inventory;

[0021] The goodness of fit is greater than or equal to 0. The closer it is to zero, the more the actual distribution fits the "ideal proportion". Then calculate according to the formula:

[0022] Size efficiency = e^(-goodness of fit)*100%.

[0023] As a further solution of the present invention, the main size ratio is a Float variable, and the value range is [0, 100%]. The calculation formula of the main size ratio is:

[0024] Main size ratio = main size number / total number of sizes * 100%.

[0025] As a further solution of the present invention, the main size inventory ratio is a Float variable, and the value range is [0, 100%]. The calculation formula of the main size inventory ratio is:

[0026] Main size inventory ratio = main size inventory / current total inventory of the SKU * 100%,

[0027] Among them, the current total inventory is obtained by summing the number of sizes under the SKU.

[0028] As a further solution of the present invention, the total inventory of main sizes is an int variable, which refers to the sum of the absolute values ​​of the inventory of the main sizes in stock.

[0029] As a further solution of the present invention, the main size uniformity ratio is a Float variable, and the value range is [0, 100%]. The calculation formula of the main size uniformity ratio is:

[0030] Main size ratio = number of main sizes currently in stock above safety stock / total number of main sizes.

[0031] As a further solution of the present invention, the method for generating the SPU indicator from the SKU indicator in S5 is as follows:

[0032] When all SKUs have the same code, they are considered to be SPUs with the same code.

[0033] in,

[0034] The size efficiency in the SPU indicator = the weighted average of the SKUs under the SPU, with the weight being the sales volume of the SKU;

[0035] The main size inventory ratio in the SPU indicator = the main size inventory sum of the SKU under the SPU / the total inventory sum;

[0036] The total inventory of main sizes in the SPU indicator = the sum of the main size inventory of the SKU under the SPU;

[0037] The proportion of main sizes in the SPU indicator = the weighted average of the SKUs under the SPU, where the weight is the sales volume of the SKU.

[0038] As a further solution of the present invention, the calculation formula of the comprehensive value of size in S6 is:

[0039] Size comprehensive value = 47.1% * main size uniformity ratio + 28.4% * size efficiency + 17.1% * main size inventory ratio + 7.4% * uniformity value;

[0040] Among them, 47.1%, 28.4%, 17.1% and 7.4% are all obtained by the TOPSIS method. The proportion of main size inventory is interval type, and its optimal stable interval is [40%, 60%], and its maximum tolerance interval is [0, 100%].

[0041] In summary, compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0042] The invention can make a comprehensive and rapid evaluation of sizes through the comprehensive value of sizes, so that people can quickly understand the golden size of commodities. At the same time, the fit degree between the current inventory and the actual sales situation is convenient for sellers to quickly understand the size quality of the current inventory, and timely replenish commodities that are out of stock or about to be out of stock, thereby reducing the losses caused by out-of-stock, facilitating manufacturers to adjust the production structure of commodities of different sizes, meeting the actual needs of customers, and having the advantages of rapid comprehensive evaluation of sizes, predicting inventory sales and being able to carry out targeted replenishment, thereby achieving the purpose of improving work efficiency and quality and reducing labor costs.

[0043] In order to more clearly illustrate the structural features and effects of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Flowchart of an embodiment of the invention.

[0045] Figure 2 Schematic diagram of the “ideal ratio” of an embodiment of the invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0047] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.

[0048] In one embodiment of the present invention, see Figure 1 , the commercial size distribution evaluation method comprises the following steps:

[0049] S1: Statistics on SKU sales;

[0050] S2: Determine the "ideal ratio", where the "ideal ratio" is obtained through chi-square test and cluster analysis, and the deviation between the sales of each size of the product and the theoretical inference value is statistically analyzed;

[0051] S3: Input the inventory of SKU and calculate various indicators, including size consistency, size efficiency, main size ratio, main size inventory ratio, main size total inventory and main size consistency ratio;

[0052] S4: Generate SKU indicator summary;

[0053] S5: Upgrade the SKU indicator to the SPU indicator;

[0054] S6: Calculate the size comprehensive value of the SPU or SKU, and output the corresponding size comprehensive value.

[0055] In this embodiment, the calculation object is SKU, that is, the color and style of the product; the calculation period defaults to one month or the first month of the new product's launch. The calculation period here can be manually modified. In step S1, by reading the .csv file, the sales situation of the size of each SKU in the sales cycle is imported, specific to the SKU, and the current inventory situation needs to be specific to the number of sizes.

[0056] In one embodiment of the present invention, see Figure 1 , the determination of the “ideal ratio” in S2 comprises the following steps:

[0057] 1) Count the sales size distribution of each SKU during the selected sales cycle, arrange them in order from small to large according to the number of sizes, and name the ratio as the sales statistical ratio; consult the brand to count the whole-hand ratio of each SKU when the factory places an order; obtain the sales ratio of the benchmark product through the data of competing products;

[0058] 2) Export the results of the above data, generate an intermediate file, analyze the rationality of the above ratios, find out the reasons for the obviously abnormal ratios, and manually modify the parts that need to be modified;

[0059] 3) Cluster analysis is performed on the above ratios to find the same pattern and determine the final "ideal ratio".

[0060] In this embodiment, if the product being sold is an evergreen product, and the evergreen product will not be out of stock, it is sufficient to select a time period of one or two natural months to count the proportion; if the product being sold is a seasonal product, it is best to count the sales proportion from the time the merchant first sold out the product; if the product being sold is a new product, the sales data since its launch can be counted, or the sales proportion of the same version of the product during the same period can be used.

[0061] In one embodiment of the present invention, see Figure 1 , the uniformity is a Boolean variable, which is defined as 1 if all sizes of the SKU are in stock above the safety stock, otherwise, it is assigned a value of 0, that is, to determine whether all sizes in the size master file are in stock;

[0062] In one embodiment of the present invention, see Figure 1 , the size efficiency is a Float variable, that is, the size in the intersection of sales and inventory, and the value range is [0, 100%]. For each SKU, the chi-square value of the current inventory size distribution and the "ideal ratio" is calculated. The calculation formula is as follows:

[0063] That is, the goodness of fit; where r refers to the number of sizes under the SKU, which is a positive integer; n refers to the number of stocks under the SKU, which is a positive integer; p k It refers to the proportion of size k in the ideal ratio, and the value is a pure decimal; np k It refers to the ideal inventory number of the product in theory according to the ideal ratio; n k It refers to the inventory number corresponding to size k in the actual inventory, which can be a positive integer or 0;

[0064] The goodness of fit is greater than or equal to 0. The closer it is to zero, the more the actual distribution fits the "ideal proportion". Then calculate according to the formula:

[0065] Size efficiency = e^(-goodness of fit)*100%,

[0066] From the above formula, we can understand that the closer the goodness of fit value is to 0, the closer the size efficiency is to 1, and the closer it is to the "ideal proportion". Among them, for the problem of merging areas, npi is required to be greater than or equal to 5, that is, the continuity-corrected chi-square test should be selected instead of the goodness of fit. For the case of merging areas, the merged area needs to be explained after the SKU; if the monthly sales volume of a SKU is less than 50, it is necessary to use Fisher's exact probability method instead of goodness of fit, and in the SKU remarks column, it should be explained that it is calculated by Fisher's exact probability method; when n is 0 or the denominator is 0, the value of the quotient is assigned to 0.

[0067] In one embodiment of the present invention, see Figure 1 , the main size ratio is a Float variable, the value range is [0, 100%], and the calculation formula of the main size ratio is:

[0068] Main size ratio = main size number / total number of sizes * 100%, where the total number of sizes is determined by the current inventory.

[0069] In one embodiment of the present invention, see Figure 1 , the main size inventory ratio is a Float variable, the value range is [0, 100%], and the calculation formula of the main size inventory ratio is:

[0070] Main size inventory ratio = main size inventory / current total inventory of the SKU * 100%,

[0071] Among them, the current total inventory is obtained by summing the number of sizes under the SKU.

[0072] In one embodiment of the present invention, see Figure 1 The total inventory of main sizes is an int variable, which refers to the sum of the absolute values ​​of the inventory of the main sizes in stock.

[0073] In one embodiment of the present invention, see Figure 1 , the main size uniformity ratio is a Float variable, the value range is [0, 100%], and the calculation formula of the main size uniformity ratio is:

[0074] Main size uniformity ratio = the number of main sizes currently in stock above the safety stock / the total number of main sizes. The closer the main size uniformity ratio is to 100%, the more main sizes are not out of stock. If the main size uniformity ratio is 100%, it means that all main sizes are in stock. Obviously, when the uniformity is 1, the main size uniformity ratio is 100%, and when the uniformity is 0, the main size uniformity ratio is not necessarily 0.

[0075] After calculating the above indicators, the above calculation results are returned and displayed in the same way as the manually modified places set by the front end. The final output file format is .csv, as shown in the following table. Each line is the size indicator of a SKU.

[0076]

[0077]

[0078] Among them, if the data is calculated using Fisher's exact probability method, it means that the total sales volume during the statistical period corresponding to the data is less than 50 pieces. If there is a merge, the content indicates that the sales volume of models XX and XX is too small, and XX and XX are the names of the merged objects. If there is no such two situations, the content of the description is empty.

[0079] In one embodiment of the present invention, see Figure 1 The method for generating the SPU indicator from the SKU indicator in S5 is:

[0080] When all SKUs have the same code, they are considered to be SPUs with the same code.

[0081] in,

[0082] The size efficiency in the SPU indicator = the weighted average of the SKUs under the SPU, with the weight being the sales volume of the SKU;

[0083] The main size inventory ratio in the SPU indicator = the main size inventory sum of the SKU under the SPU / the total inventory sum;

[0084] The total inventory of main sizes in the SPU indicator = the sum of the main size inventory of the SKU under the SPU;

[0085] The proportion of main sizes in the SPU indicator = the weighted average of the SKUs under the SPU, where the weight is the sales volume of the SKU.

[0086] In one embodiment of the present invention, see Figure 1 , the calculation formula of the comprehensive value of size in S6 is:

[0087] Size comprehensive value = 47.1% * main size uniformity ratio + 28.4% * size efficiency + 17.1% * main size inventory ratio + 7.4% * uniformity value;

[0088] Among them, the proportion of main size inventory is interval type, its optimal stable interval is [40%, 60%], and its maximum tolerance interval is [0, 100%]. The indicator needs to be positive. The category level here can be manually modified according to actual needs to make it meet actual needs, as shown in the following table.

[0089] Main size ratio Size Efficiency Main size inventory ratio Optimal Solution Column Maximum Column Maximum The maximum value after positive transformation Worst solution Column minimum value Column minimum value The minimum value of the column after forward transformation Weight (tentative) 0.471 0.284 0.171

[0090] In this embodiment, the output data format is agreed upon, and the calculated size comprehensive value is output, wherein the following areas are used to interact with the front end: the number of safety stocks, which defaults to 2; the statistical period, which defaults to the period span of the input file; the "ideal ratio" for calculating the goodness of fit, which can be modified in the intermediate file, which defaults to the intermediate file, that is, the sales statistical ratio of each size; the number of pieces of inventory that can be calculated to calculate the size comprehensive value, which defaults to 50 pieces; the output of the intermediate file can not only manually modify the ideal ratio, but also speed up the calculation. The parameters that can be written into the background script example include: the weights of each indicator of the size comprehensive value; the reasonable range of the proportion of the main size inventory in the size comprehensive value; by default, when the sales volume is greater than 20, the sales statistical ratio is used as the ideal ratio, and when the sales volume is less than 20, the whole hand ratio is used as the ideal ratio.

[0091] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A commercial size distribution evaluation method, characterized in that: The following steps are involved: S1: Statistics on SKU sales; S2: Determine the "ideal ratio"; S3: Input the inventory of SKU and calculate various indicators, including size consistency, size efficiency, main size ratio, main size inventory ratio, main size total inventory and main size consistency ratio; S4: Generate SKU indicator summary; S5: Upgrade the SKU indicator to the SPU indicator; S6: Calculate the size comprehensive value of the SPU or SKU, and output the corresponding size comprehensive value; Determining the "ideal ratio" in S2 includes the following steps: 1) Count the sales size distribution of each SKU during the selected sales cycle, arrange them in order from small to large according to the number of sizes, and name the ratio as the sales statistical ratio; consult the brand to count the whole-hand ratio of each SKU when the factory places an order; obtain the sales ratio of the benchmark product through the data of competing products; 2) Export the results of the above data, generate an intermediate file, analyze the rationality of the above ratios, find out the reasons for the obviously abnormal ratios, and manually modify the parts that need to be modified; 3) Cluster analysis is performed on the above ratios to find the same pattern and determine the final "ideal ratio"; 4) The uniformity is a Boolean variable, which is defined as 1 if all sizes of the SKU are in stock above the safety stock. Otherwise, the uniformity is assigned a value of 0, that is, to determine whether all sizes in the size master file are in stock; 5) The size efficiency is a Float variable, that is, the size at the intersection of sales and inventory, with a value range of [0, 100%]. For each SKU, the chi-square value of the current inventory size distribution and the "ideal ratio" is calculated. The calculation formula is as follows: is the goodness of fit; where r refers to the number of sizes under the SKU; n refers to the number of stocks under the SKU; p k It refers to the proportion of size k in the ideal proportion; np k It refers to the ideal inventory number of the product in theory according to the ideal ratio; n k It refers to the inventory number corresponding to size k in the actual inventory; The goodness of fit is greater than or equal to 0. The closer it is to zero, the more the actual distribution fits the "ideal proportion". Then calculate according to the formula: Size efficiency = e^(-goodness of fit)*100%; The main size ratio is a Float variable with a value range of [0, 100%]. The calculation formula for the main size ratio is: Main size ratio = main size number / total number of sizes * 100%; The main size inventory ratio is a Float variable with a value range of [0, 100%]. The calculation formula for the main size inventory ratio is: Main size inventory ratio = main size inventory / current total inventory of the SKU * 100%, Among them, the current total inventory is obtained by summing the number of sizes under the SKU; The total number of main size stocks is an int variable, which refers to the sum of the absolute values ​​of the stocks of the main sizes in stock; The main size uniformity ratio is a Float variable, and the value range is [0, 100%]. The calculation formula of the main size uniformity ratio is: Main size ratio = the number of main sizes in stock above the safety stock / the total number of main sizes; The method of generating SPU index from SKU index in S5: When all SKUs have the same code, they are considered to be SPUs with the same code. in, The size efficiency in the SPU indicator = the weighted average of the SKUs under the SPU, with the weight being the sales volume of the SKU; The main size inventory ratio in the SPU indicator = the main size inventory sum of the SKU under the SPU / the total inventory sum; The total inventory of main sizes in the SPU indicator = the sum of the main size inventory of the SKU under the SPU; The main size ratio in the SPU indicator = the weighted average of the SKUs under the SPU, with the weight being the sales volume of the SKU; The calculation formula of the comprehensive value of size in S6 is: Size comprehensive value = 47.1% * main size uniformity ratio + 28.4% * size efficiency + 17.1% * main size inventory ratio + 7.4% * uniformity value; Among them, 47.1%, 28.4%, 17.1% and 7.4% are all obtained by the TOPSIS method. The proportion of main size inventory is interval type, and its optimal stable interval is [40%, 60%], and its maximum tolerance interval is [0, 100%].

Images