Optimize shopping route using purchase embeddings

1. A computer implemented method for suggesting alternative sources of goods or services, the method comprising:

receiving information identifying purchases, by a user, of a first plurality of items, wherein the information comprises data records in a multi-dimensional space relating to the first plurality of items;

identifying, based on the information, a correlation between the purchases of the first plurality of items, wherein the correlation shows a purchasing pattern of the user within a first geographic region;

detecting a second geographic region that includes a location of the user;

querying one or more databases for descriptions of a second plurality of items;

calculating, based on the descriptions and the received information identifying purchases, measures of similarity between the first and the second pluralities of items;

identifying, using a machine learning model and based on the descriptions and the calculating, a subset of the second plurality of items that are available for purchase within the second geographic region and that have measures of similarity to the first plurality of items that exceed predetermined thresholds;

generating, based on the identifying of the correlation and the identifying of the subset, a proposed pattern for purchasing the subset within the second geographic region, wherein the proposed pattern provides one or more vendor locations within the second geographic region at which the subset is sold;

sending, based on the proposed pattern exceeding a rating based on one or more metrics relating to the proposed pattern and to a device associated with the user, instructions with the proposed pattern for purchasing the subset;

receiving purchase information relating to the proposed pattern for purchasing the subset; and

updating the machine learning model based on the received purchase information and the generated proposed pattern.

2. The computer implemented method of claim 1 , further comprising:

limiting the one or more vendor locations to within a predetermined distance of the location of the user;

limiting the one or more vendor locations to a single common location;

limiting a distance between the one or more vendor locations;

providing, in the proposed pattern, a sequence to purchase items in the subset;

providing in the proposed pattern a proposed route between the one or more vendor locations; or

providing in the proposed pattern a time frame within when to purchase the subset.

3. The computer implemented method of claim 1 , further comprising:

identifying a possible location where one item in the subset may be purchased; and

selecting, based on one or more criteria, the possible location as one of the one or more vendor locations, wherein the one or more criteria include:

the possible location being identified as a small business,

a toll road being excluded in a route to the possible location,

the possible location being within a predefined distance to the location of the user,

the possible location being within a predefined distance to another one of the one or more vendor locations, or the possible location being identical to another one of the one or more vendor locations.

4. The computer implemented method of claim 1 , further comprising:

identifying possible locations where one item of the subset may be purchased;

receiving, via the device, a user preference; and

selecting, based on the user preference, one of the possible locations as one of the one or more vendor locations.

5. The computer implemented method of claim 1 , further comprising:

comparing the proposed pattern to the purchasing pattern; and

evaluating, based on the comparing, the proposed pattern according to one or more metrics, wherein the sending of the instructions to the device is based on the proposed pattern exceeding a predetermined rating according to the one or more metrics.

6. The computer implemented method of claim 5 , wherein the proposed pattern exceeding the predetermined rating indicates a travel time, a travel distance, a purchase cost, or a sales tax being lower for the subset than for the first plurality of items.

7. The computer implemented method of claim 1 , further comprising

ranking the measures of similarity between the first and the second pluralities of items, wherein the predetermined thresholds comprise a predetermined minimum ranking.

8. The computer implemented method of claim 1 , wherein the descriptions of the second plurality of items identify at least one of:

one or more geographic regions where one of the second plurality of items may be purchased,

a vendor location where one of the second plurality of items may be purchased,

a vendor identified as a small business where one of the second plurality of items may be purchased,

a class of goods or services of one of the second plurality of items, a similar item to one of the second plurality of items, or

an alternate name for one of the second plurality of items.

9. The computer implemented method of claim 1 , further comprising:

identifying a first time frame when the purchases of the first plurality of items occurred; and

including, based on the first time frame, a second time frame in the proposed pattern of when to purchase the subset.

10. The computer implemented method of claim 1 , wherein the correlation between the purchases of the first plurality of items is based on:

a common class of goods or services of two of the first plurality of items;

distances traveled for the purchases of the first plurality of items;

amounts paid for the purchases of the first plurality of items;

geographic areas where the purchases of the first plurality of items occurred;

time frames when the purchases of the first plurality of items occurred;

frequencies of repeated purchases of the first plurality of items;

durations between two of the purchases of the first plurality of items;

distances between where the purchases of the first plurality of items occurred; or

methods of payment for the purchases of the first plurality of items.

11. The method of claim 1 , wherein the multi-dimensional space comprises a tulple.

12. A server comprising:

at least one computer processor; and

computer memory comprising computer-executable instructions that when executed by the at least one computer processor, cause the server to:

receive information identifying purchases, by a user, of a first plurality of items, wherein the information comprises data records in a multi-dimensional space relating to the first plurality of items;

identify, based on the information, a correlation between the purchases of the first plurality of items, wherein the correlation shows a purchasing pattern of the user within a first geographic region;

detect a second geographic region that includes a location of the user;

query one or more databases for descriptions of a second plurality of items;

calculate, based on the descriptions, measures of similarity between the first and the second pluralities of items;

identify, using a machine learning model and based on the descriptions and the calculating, a subset of the second plurality of items that are available for purchase within the second geographic region and that have measures of similarity to the first plurality of items that exceed predetermined thresholds;

generate, based on the identifying of the correlation and the identifying of the subset, a proposed pattern for purchasing the subset within the second geographic region, wherein the proposed pattern provides one or more vendor locations within the second geographic region at which the subset is sold;

send, based on the proposed pattern exceeding a rating based on one or more metrics relating to the proposed pattern and to a device associated with the user, instructions including the proposed pattern for purchasing the subset;

receive purchase information relating to the proposed pattern for purchasing the subset; and

update the machine learning model based on the received purchase information and the generated proposed pattern.

13. The server of claim 12 ,

wherein the proposed pattern provides one or more vendor locations within the second geographic region at which the subset is sold; and

wherein the computer-executable instructions, when executed by the at least one computer processor, further cause the server to:

limit the one or more vendor locations to within a predetermined distance of the location of the user;

limit the one or more vendor locations to a single common location;

limit a distance between the one or more vendor locations;

provide in the proposed pattern a sequence to purchase items in the subset;

provide the proposed pattern a proposed route between the one or more vendor locations; or

provide in the proposed pattern a time frame within when to purchase the subset.

14. The server of claim 12 , wherein the computer-executable instructions, when executed by the at least one computer processor, further cause the server to:

compare the proposed pattern to the purchasing pattern; and

evaluate, based on the comparing, the proposed pattern according to one or more metrics, wherein the instructions are based on the proposed pattern exceeding a predetermined rating according to the one or more metrics.

15. The server of claim 14 , wherein the proposed pattern exceeding the predetermined rating indicates a travel time, a travel distance, a purchase cost, or a sales tax being lower for the subset than for the first plurality of items.

16. The server of claim 12 , wherein the computer-executable instructions, when executed by the at least one computer processor, further cause the server to:

rank the measures of similarity between the first and the second pluralities of items, wherein the predetermined thresholds comprise a predetermined minimum ranking.

17. The server of claim 12 , wherein the descriptions of the second plurality of items identify at least one of:

one or more geographic regions where one of the second plurality of items may be purchased,

a vendor location where one of the second plurality of items may be purchased,

a vendor identified as a small business where one of the second plurality of items may be purchased,

a class of goods or services of one of the second plurality of items, a similar item to one of the second plurality of items, or

an alternate name for one of the second plurality of items.

18. The server of claim 12 , wherein the computer-executable instructions, when executed by the at least one computer processor, further cause the server to:

identify a first time frame when the purchases of the first plurality of items occurred; and

include, based on the first time frame, a second time frame in the proposed pattern of when to purchase the subset.

19. A method for suggesting alternative sources of goods or services, the method comprising:

receiving information identifying purchases, by a user, of a first plurality of items, wherein the information comprises data records in a multi-dimensional space, wherein the information comprises data records in a multi-dimensional space relating to the first plurality of items;

identifying, based on the information, a correlation between the purchases of the first plurality of items, wherein the correlation shows a purchasing pattern of the user within a first geographic region;

detecting a second geographic region that includes a location of the user;

querying one or more databases for descriptions of a second plurality of items;

calculating, based on the descriptions, measures of similarity between the first and the second pluralities of items;

identifying, using a machine learning model trained to determine similarity between items based on a multi-dimensional space, a subset of the second plurality of items that are available for purchase within the second geographic region and that have a measure of similarity to the first plurality of items that exceed predetermined thresholds, wherein the machine learning model is trained based on:

the descriptions,

a set of training information, and

the calculating;

generating, based on the identifying of the correlation and the identifying of the subset, a proposed pattern for purchasing the subset within the second geographic region, wherein the proposed pattern provides one or more vendor locations within the second geographic region at which the subset is sold; and

sending, based on the proposed pattern exceeding a rating based on one or more metrics relating to the proposed pattern and to a device associated with the user, instructions with the proposed pattern for purchasing the subset;

receiving purchase information relating to the proposed pattern for purchasing the subset; and

updating the machine learning model based on the received purchase information and the generated proposed pattern.

20. The method of claim 11 , further comprising:

comparing the proposed pattern to the purchasing pattern; and

evaluating, based on the comparing, the proposed pattern according to one or more metrics, wherein the sending of the instructions to the device is based on the proposed pattern exceeding a predetermined rating according to the one or more metrics.