System and method of an attribute-value combination and assortment planner
A system and method are disclosed for generating an assortment plan by an assortment planner. The assortment planner stores value metrics for two or more products, each of the products including two or more of attributes. The assortment planner also analyzes the two or more attributes, by generating attribute values for each of the two or more attributes and communicates the attribute values for each of the two or more attributes to a planning engine. The assortment planner also further constructs a product attributes table and a value metrics table, duplicates the attribute values to generate a merged product attributes table including a number of duplicates of the attribute values and generates a binary value table for each of the attribute values, one or more itemsets, and an assortment of products based, at least in part, on the one or more itemsets. Other embodiments are also disclosed.
1. A method of assortment planning, comprising:
storing, by a computer comprising a processor and a memory, value metrics for two or more products, each of the products characterized by two or more attributes;
generating, by the computer, attribute values for each of the two or more attributes;
constructing, by the computer, a product attributes table and a value metrics table;
generating, by the computer, a binary value table for each of the attribute values, one or more itemsets, and an assortment of products based on the one or more itemsets, wherein each itemset comprises an attribute-value combination of a particular size, and further wherein the particular size represents a number of attribute values in the itemset;
performing, by the computer, a first iteration that enumerates all possible itemsets of minimum size and further removes itemsets from the enumeration with a support below a minimum support value to generate remaining itemsets, wherein a support value for a product represents a frequency of occurrence of that product in the product attributes table;
performing, by the computer, a second iteration on the remaining itemsets to increment a size of the remaining itemsets and further remove itemsets from the incremented remaining itemsets with a support below a minimum support value;
repeating, by the computer, the second iteration until a stopping criteria is met resulting in generating an optimal set of itemsets indicating an optimal assortment of products, wherein the optimal set of itemsets does not include the removed itemsets; and
initiating, by the computer, manufacturing of at least one of the products at one or more supply chain entities.
2. The method of claim 1 , further comprising:
generate, based on the optimal assortment of products, one or more of:
an assortment plan incorporating sales or profitability, orders for an attribute-value combination having a highest value according to a value metric, and sending a stop order for attribute-value combinations having a lowest value according to a value metric.
3. The method of claim 1 , wherein the two or more attributes are organized in a hierarchy according to one or more of classes, subclasses, categories, subcategories and departments.
4. The method of claim 1 , further comprising:
generating, by the computer, one or more charts, graphs, or plots illustrating how sales or profitability relate to the optimal assortment of products including one or more attribute-value combinations.
5. The method of claim 4 , further comprising:
filtering, by the computer, data displayed on the one or more charts, graphs or plots based on one or more different dimensions of segments, time-periods, product types, stores, channels, departments, seasons and attributes.
6. The method of claim 1 , wherein the product attributes table comprises one or more of a time dimension, a location dimension and a customer segmentation dimension.
7. The method of claim 1 , wherein the value metrics table comprises one or more of sales, sales of units, profits, promotional sales units, promotional sale dollars and number of returns.
8. A system configured to provide an assortment plan of two or more products, comprising:
a computer comprising a processor and a memory, the computer configured to store value metrics for two or more products, each of the products characterized by two or more attributes;
the computer configured to:
generating attribute values for each of the two or more attributes; and
construct a product attributes table and a value metrics table;
generate a binary value table for each of the attribute values, one or more itemsets, and an assortment of products based, at least in part, on the one or more itemsets, wherein each itemset comprises an attribute-value combination of a particular size, and further wherein the particular size represents a number of attribute values in the itemset;
perform a first iteration that enumerates all possible itemsets of minimum size and further removes itemsets from the enumeration with a support below a minimum support value to generate remaining itemsets, wherein a support value for a product represents a frequency of occurrence of that product in the product attributes table;
perform a second iteration on the remaining itemsets to increment a size of the remaining itemsets and further remove itemsets from the incremented remaining itemsets with a support below a minimum support value;
repeat the second iteration until a stopping criteria is met resulting in generating an optimal set of itemsets indicating an optimal assortment of products, wherein the optimal set of itemsets does not include removed the itemsets; and
initiate manufacturing of at least one of the products at one or more supply chain entities.
9. The system of claim 8 , wherein the computer is further configured to:
generate, based on the optimal assortment of products, one or more of:
an assortment plan incorporating sales or profitability, orders for an attribute-value combination having a highest value according to a value metric, and sending a stop order for attribute-value combinations having a lowest value according to a value metric.
10. The system of claim 8 , wherein the two or more attributes are organized in a hierarchy according to one or more of classes, subclasses, categories, subcategories and departments.
11. The system of claim 8 , wherein the computer is further configured to:
generating one or more charts, graphs, or plots illustrating how sales or profitability relate to the optimal assortment of products including one or more attribute-value combinations.
12. The system of claim 11 , wherein the computer is further configured to:
filter data displayed on the one or more charts, graphs or plots based on one or more different dimensions of segments, time-periods, product types, stores, channels, departments, seasons and attributes.
13. The system of claim 8 , wherein the product attributes table comprises one or more of a time dimension, a location dimension and a customer segmentation dimension.
14. The system of claim 8 , wherein the value metrics table comprises one or more of sales, sales of units, profits, promotional sales units, promotional sale dollars and number of returns.
15. A non-transitory computer-readable medium embodied with software, the software when executed configured to:
generate an assortment plan of two or more products by:
storing value metrics for two or more products, each of the products characterized by two or more attributes;
generating attribute values for each of the two or more attributes;
constructing a product attributes table and a value metrics table;
generating a binary value table for each of the attribute values, one or more itemsets, and an assortment of products based, at least in part, on the one or more itemsets, wherein each itemset comprises an attribute-value combination of a particular size, and further wherein the particular size represents a number of attribute values in the itemset;
performing a first iteration that enumerates all possible itemsets of minimum size and further removes itemsets from the enumeration with a support below a minimum support value to generate remaining itemsets, wherein a support value for a product represents a frequency of occurrence of that product in the product attributes table;
performing a second iteration on the remaining itemsets to increment a size of the remaining itemsets and further remove itemsets from the incremented remaining itemsets with a support below a minimum support value;
repeating the second iteration until a stopping criteria is met resulting in generating an optimal set of itemsets indicating an optimal assortment of products, wherein the optimal set of itemsets does not include the removed itemsets; and
initiating manufacturing of at least one of the products at one or more supply chain entities.
16. The non-transitory computer-readable medium of claim 15 , wherein the software when executed is further configured to:
generate, based on the optimal assortment of products, one or more of:
an assortment plan incorporating sales or profitability, orders for an attribute-value combination having a highest value according to a value metric, and sending a stop order for attribute-value combinations having a lowest value according to a value metric.
17. The non-transitory computer-readable medium of claim 15 , wherein the two or more attributes are organized in a hierarchy according to one or more of classes, subclasses, categories, subcategories and departments.
18. The non-transitory computer-readable medium of claim 15 , wherein the software when executed is further configured to:
generate one or more charts, graphs, or plots illustrating how sales or profitability relate to the optimal assortment of products including one or more attribute-value combinations.
19. The non-transitory computer-readable medium of claim 18 , wherein the software when executed is further configured to:
filter data displayed on the one or more charts, graphs or plots based on one or more different dimensions of segments, time-periods, product types, stores, channels, departments, seasons and attributes.
20. The non-transitory computer-readable medium of claim 15 , wherein the product attributes table comprises one or more of a time dimension, a location dimension and a customer segmentation dimension.