Generation of a sequence of related text-based search queries

1. A method for generating a sequence of related text-based search queries, the method comprising:

extracting a plurality of attributes of a source item from item information related to the source item;

generating a first text-based query comprising a first subset of the plurality of attributes;

searching for a first group of competitor items using the first text-based query;

determining that the first group of competitor items has a number of items that is below a desired number of search results;

generating a second text-based query comprising a second subset of the plurality of attributes, wherein the second subset of the plurality of attributes contains fewer of the plurality of attributes than the first subset of the plurality of attributes, wherein the first text-based query and the second text-based query are generated using the plurality of attributes extracted from the item information related to the source item; and

searching for a second group of competitor items using the second text-based query, wherein the second group of competitor items includes a greater number of items than the first group of competitor items.

2. The method of claim 1 , further comprising:

determining that the second group of competitor items has a number of items that is below the desired number of search results;

generating a third text-based query comprising a third subset of the plurality of attributes, wherein the third subset of the plurality of attributes contains fewer of the plurality of attributes than the second subset of the plurality of attributes; and

searching for a third group of competitor items using the third text-based query, wherein the third group of competitor items includes a greater number of items than the second group of competitor items.

3. The method of claim 1 , further comprising computing similarity scores between the source item and each of the second group of competitor items based on at least one common feature between the source item and each of the second group of competitor items.

4. The method of claim 3 , wherein the at least one common feature is related to at least one of the second subset of the plurality of attributes.

5. The method of claim 3 , wherein the computing of the similarity scores further comprises determining a value for a degree of similarity of the at least one common feature between the source item and each of the second group of competitor items.

6. The method of claim 5 , wherein the computing of the similarity scores further comprises multiplying the value for the degree of similarity by a weight value associated with the at least one common feature.

7. The method of claim 6 , wherein the computing of the similarity scores further comprises:

determining a second value for a second degree of similarity between the source item and each of the second group of competitor items of a second common feature of the at least one common feature;

multiplying the second value by a second weight value associated with the second common feature; and

summing resulting values of the multiplying of the value by the weight value and the multiplying of the second value by the second weight value.

8. The method of claim 3 , further comprising determining a most similar item from the second group of competitor items that is most similar to the source item based on the similarity scores.

9. The method of claim 1 , wherein the item information related to the source item comprises unstructured text related to the source item.

10. The method of claim 1 , further comprising determining a priority level of at least two priority levels for each of the plurality of attributes.

11. The method of claim 10 , wherein the generating of the second text-based query further comprises removing at least one of the first subset of the plurality of attributes that has a lower priority level than other attributes of the first subset of the plurality of attributes to yield the second subset of the plurality of attributes.

12. The method of claim 10 , wherein the at least two priority levels comprise at least three priority levels, and wherein the at least three priority levels are determined according to a non-binary schema.

13. The method of claim 1 , wherein the searching for the first group of competitor items comprises searching one or more competitor domains associated with one or more competitors.

14. The method of claim 1 , wherein the source item is offered for sale on a first source domain and the first group of competitor items are offered for sale on one or more competitor domains that are different from the first source domain.

15. A system comprising:

a processor; and

a non-transitory computer-readable medium having stored thereon instructions that are executable by the processor to cause the system to perform operations comprising:

extract a plurality of attributes of a source item from item information related to the source item;

generate a first text-based query comprising a first subset of the plurality of attributes;

search for a first group of competitor items using the first text-based query;

determine that the first group of competitor items has a number of items that is below a desired number of search results;

generate a second text-based query comprising a second subset of the plurality of attributes, wherein the second subset of the plurality of attributes contains fewer of the plurality of attributes than the first subset of the plurality of attributes, wherein the first text-based query and the second text-based query are generated using the plurality of attributes extracted from the item information related to the source item; and

search for a second group of competitor items using the second text-based query, wherein the second group of competitor items includes a greater number of items than the first group of competitor items.

16. The system of claim 15 , wherein the instructions further cause the system to perform operations comprising:

determine that the second group of competitor items has a number of items that is below the desired number of search results;

generate a third text-based query comprising a third subset of the plurality of attributes, wherein the third subset of the plurality of attributes contains fewer of the plurality of attributes than the second subset of the plurality of attributes; and

search for a third group of competitor items using the third text-based query, wherein the third group of competitor items includes a greater number of items than the second group of competitor items.

17. The system of claim 15 , wherein the instructions further cause the system to perform operations comprising:

compute similarity scores between the source item and each of the second group of competitor items based on at least one common feature between the source item and each of the second group of competitor items.

18. The system of claim 17 , wherein the computation of the similarity scores further comprises:

determine a value for a degree of similarity of the at least one common feature between the source item and each of the second group of competitor items.

19. The system of claim 18 , wherein the computation of the similarity scores further comprises:

multiply the value for the degree of similarity by a weight value associated with the at least one common feature.

20. The system of claim 17 , wherein the instructions further cause the system to perform operations comprising:

determine a most similar item from the second group of competitor items that is most similar to the source item based on the similarity scores.

21. The system of claim 15 , wherein the instructions further comprise the system to perform operations comprising:

determine a priority level of at least two priority levels for each of the plurality of attributes.

22. The system of claim 21 , wherein the generation of the second text- based query further comprises:

remove at least one of the first subset of the plurality of attributes that has a lower priority level than other attributes of the first subset of the plurality of attributes to yield the second subset of the plurality of attributes.