Systems and methods for intelligent promotion design with promotion scoring

1. A method for scoring a set of promotions comprising:

receiving, by one or more processors, a set of training offers comprising a plurality of variables, each variable having one of a set of values to form a combination of variable values;

converting, by the one or more processors, the combination of variable values for each of the training offers into a vector;

generating, by the one or more processors, pairings of the training offers such that all combinations of training offer pairs is represented;

subtracting, by the one or more processors, the vector of one training offer in each pair from the other vector of the other training offer of the pair to generate a pair vector;

collecting, by the one or more processors, success metrics for each of the training offers from a retailer's point of sales system, a computerized application, and from consumer mobile devices;

subtracting, by the one or more processors, the success metrics of the one training offer in each pair from the other success metrics of the other training offer of the pair to generate a raw score;

generating, by the one or more processors, a normalized score for each of the pairings using the raw score and the pair vector;

determining, by the one or more processors, that the set of training offers consists of offers originating from a single client;

responsive to the determination that set of training offers consists of offers originating from a single client, generating, by the one or more processors, a decision tree model by machine learning and using the normalized scores, wherein the one or more processors are configured to generate one of two model types dependent upon at least one of the amount of training offers in the set of training offers or the number of clients the offers in the set of training offers originate from, wherein the two model types are a decision tree and a neural network; and

applying, by the one or more processors, the model to a set of new offers to generate a score for each new offer.

2. The method of claim 1 , wherein the one or more processors are configured to generate a neural network when the set of training offers consists of offers originating from multiple clients.

3. The method of claim 1 , wherein the success metrics include a klip rate, redemption rate, viewing rate, saving rate, sharing rate and impression measure.

4. The method of claim 3 , wherein the success metrics are consolidated as a weighted average.

5. The method of claim 1 , wherein applying the model comprises utilizing linear regression.

6. The method of claim 5 , wherein applying the model comprises generating an estimate and a t-value.

7. The method of claim 6 , wherein the generated score is the estimate.

8. The method of claim 6 , wherein the generated score is the t-value.

9. The method of claim 1 further comprising ranking, by the one or more processors, the new offers by their scores; and generating a set of top ranked offers, wherein the set of top ranked new offers is between 4 and 10 offers.

10. The method of claim 1 further comprising ranking, by the one or more processors, the new offers by their scores; and generating a set of top ranked offers, wherein the set of top ranked new offers is the highest 10-30% of the set of new offers.

11. A method for scoring a set of promotions comprising:

receiving, by one or more processors, a set of training offers comprising a plurality of variables;

collecting, by the one or more processors, success metrics for each training offer;

subtracting, by the one or more processors, the success metrics of each training offer from the success metrics of each other training offer to generate raw scores;

pairing, by the one or more processors, the training offer to generate pairings;

generating, by the one or more processors, a normalized score for each of the pairings using the raw scores;

determining, by the one or more processors, that the set of training offers consists of offers originating from multiple clients;

responsive to the determination that set of training offers consists of offers originating from multiple clients, generating, by the one or more processors, a neural network model by machine learning and using the normalized scores, wherein the one or more processors are configured to generate one of two model types dependent upon at least one of the amount of training offers in the set of training offers or the number of clients the offers in the set of training offers originate from, wherein the two model types are a decision tree and a neural network; and

applying, by the one or more processors, the model to a set of new offers to generate a predicted score for each new offer.

12. The method of claim 11 , wherein the one or more processors are configured to generate a decision tree when the set of training offers consists of offers originating from a single client.

13. The method of claim 11 , wherein the success metrics include a klip rate, redemption rate, viewing rate, saving rate, sharing rate and impression measure.

14. The method of claim 11 , wherein the success metrics are consolidated as a weighted average.

15. The method of claim 11 , wherein applying the model comprises utilizing a linear regression.

16. The method of claim 14 , wherein applying the model comprises generating an estimate and a t-value.

17. The method of claim 15 , wherein the predicted score is the estimate.

18. The method of claim 15 , wherein the predicted score is the t-value.

19. The method of claim 11 , further comprising ranking, by the one or more processors, the new offers by their scores; and

generating a set of top ranked offers, wherein the set of top ranked new offers is between 4 and 10 offers.

20. The method of claim 11 , further comprising ranking the new offers by their scores; and generating a set of top ranked offers, wherein the set of top ranked new offers is the highest 10-30% of the set of new offers.