Method, apparatus, and computer program product for forecasting demand using real time demand

1. A method comprising:

capturing user search data from a user device, the user search data captured during an interaction between the user device and a promotion and marketing service website or application, wherein the capturing of the user search data comprises receiving information via an input at a user interface displayed on the user device and extracting at least location specific data and a category or sub-category data from the information received via the input,

wherein the user search data is captured from browsing activity and character input, wherein the browsing activity includes icon selection and navigation of a hierarchal structure presented as the promotion and marketing service website or application, and

wherein the at least location specific data is a location of the user device;

storing, in a user search data database, the user search data with other user search data, the other user search data captured from one or more other user devices;

calculating, via a processor, a real-time demand using data stored in the user search data database,

wherein the calculation of the real-time demand comprises:

generating an identification pair for the user search data, the identification pair comprising a first classification and a second classification, the first classification identifying at least a category of promotion, and the second classification identifying a location identified by the location specific data; and

distributing the real-time demand to multiple hyper-locations within the location identified by the location specific data, multiple sub-categories among the category of the promotion, and multiple price points; and

determining, via the processor, the real time demand on a per category or sub-category, per location or hyper-location, and per price range basis.

2. The method of claim 1 , wherein the first classification is generated by:

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories.

3. The method of claim 1 , further comprising:

calculating a predicted demand for at least one promotion tuple, for a specified time period, wherein the predicted demand is representative of an estimated number of units to be sold during the specified time period, and wherein the promotion tuple comprises information indicative of a category or sub-category, a location, and a price range,

wherein the predicted demand is calculated by:

generating a virtual promotion, wherein the virtual promotion comprises a combination of a category or sub-category, a location, and a price range;

calculating a probability that a particular consumer would buy the virtual offer in a predetermined time period, wherein the probability is generated at least based on historical data related to the particular consumer and one or more related consumers;

determining an estimated number of units to be sold for the virtual offer as a function of at least the probability, the estimated number of units representing the predicted demand.

4. The method of claim 1 , wherein the calculation of the real-time demand further comprises:

identifying a benchmark conversion rate;

comparing the real time demand to the benchmark conversion rate to set a modified real time demand that identifies a quantity of units that would have been purchased had the units been available;

identifying an actual purchase quantity; and

modifying the real time demand, wherein the real time demand is equal to the actual purchase quantity subtracted from the modified real time demand.

5. The method of claim 3 , the method further comprising:

determining, via the processor, a total demand, on a per category or sub-category, per location or hyper-location, and per price range basis by summing the predicted demand and the real time demand.

6. The method of claim 1 , wherein the first classification is derived from captured browsing activity and text input and the second classification is derived from any of global positioning system (GPS) data indicative of a location from the user device, character input indicative of the location of the user device, or profile data associated with the user device indicative of the location of the user device.

7. The method of claim 1 , wherein the distribution of the real-time demand among the multiple hyper-locations, multiple sub-categories, and multiple price points is performed in accordance with a current distribution of units among the multiple hyper-locations, the multiple sub-categories, and the multiple price points within the high level location and the category or sub-category.

8. A computer program product comprising at least one computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions for:

capturing user search data from a user device, the user search data captured during an interaction between the user device and a promotion and marketing service website or application, wherein the capturing of the user search data comprises receiving information via an input at a user interface displayed on the user device and extracting at least location specific data and a category or sub-category data from the information received via the input,

wherein the user search data is captured from browsing activity and character input, wherein the browsing activity includes icon selection and navigation of a hierarchal structure presented as the promotion and marketing service website or application, and

wherein the at least location specific data is a location of the user device

storing, in a user search data database, the user search data with other user search data, the other user search data captured from one or more other user devices;

calculating, via a processor, a real-time demand using data stored in the user search data database,

wherein the calculation of the real-time demand comprises:

generating an identification pair for the user search data, the identification pair comprising a first classification and a second classification, the first classification identifying at least a category of promotion, and the second classification identifying a location identified by the location specific data; and

distributing the real-time demand to multiple hyper-locations within the location identified by the location specific data, multiple sub-categories among the category of the promotion, and multiple price points; and

determining, via the processor, the real time demand on a per category or sub-category, per location or hyper-location, and per price range basis.

9. The computer program product of claim 8 , wherein the first classification is generated by:

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories.

10. The computer program product of claim 8 , wherein the computer-executable program code instructions for the selecting of the one or more virtual offers further comprise program code instructions for:

calculating a predicted demand for at least one promotion tuple, for a specified time period, wherein the predicted demand is representative of an estimated number of units to be sold during the specified time period, and wherein the promotion tuple comprises information indicative of a category or sub-category, a location, and a price range,

wherein the predicted demand is calculated by:

generating a virtual promotion, wherein the virtual promotion comprises a combination of a category or sub-category, a location, and a price range;

calculating a probability that a particular consumer would buy the virtual offer in a predetermined time period, wherein the probability is generated at least based on historical data related to the particular consumer and one or more related consumers;

determining an estimated number of units to be sold for the virtual offer as a function of at least the probability, the estimated number of units representing the predicted demand.

11. The computer program product of claim 8 , wherein the calculation of the real-time demand further comprises:

identifying a benchmark conversion rate;

comparing the real time demand to the benchmark conversion rate to set a modified real time demand that identifies a quantity of units that would have been purchased had the units been available;

identifying an actual purchase quantity; and

modifying the real time demand, wherein the real time demand is equal to the actual purchase quantity subtracted from the modified real time demand.

12. The computer program product of claim 10 , wherein the calculation of the real-time demand further comprises:

determining, via the processor, a total demand, on a per category or sub-category, per location or hyper-location, and per price range basis by summing the predicted demand and the real time demand.

13. The computer program product of claim 8 , wherein the first classification is derived from captured browsing activity and text input and the second classification is derived from any of global positioning system (GPS) data indicative of a location from the user device, character input indicative of the location of the user device, or profile data associated with the user device indicative of the location of the user device.

14. The computer program product of claim 8 , wherein the distribution of the real-time demand among the multiple hyper-locations, multiple sub-categories, and multiple price points is performed in accordance with a current distribution of units among the multiple hyper-locations, the multiple sub-categories, and the multiple price points within the high level location and the category or sub-category.

15. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:

capture user search data from a user device, the user search data captured during an interaction between the user device and a promotion and marketing service website or application, wherein the capturing of the user search data comprises receiving information via an input at a user interface displayed on the user device and extracting at least location specific data and a category or sub-category data from the information received via the input,

wherein the user search data is captured from browsing activity and character input, wherein the browsing activity includes icon selection and navigation of a hierarchal structure presented as the promotion and marketing service website or application, and

wherein the at least location specific data is a location of the user device

store, in a user search data database, the user search data with other user search data, the other user search data captured from one or more other user devices;

calculate, via a processor, a real-time demand using data stored in the user search data database,

wherein the calculation of the real-time demand comprises:

generating an identification pair for the user search data, the identification pair comprising a first classification and a second classification, the first classification identifying at least a category of promotion, and the second classification identifying a location identified by the location specific data; and

distributing the real-time demand to multiple hyper-locations within the location identified by the location specific data, multiple sub-categories among the category of the promotion, and multiple price points; and

determine, via the processor, the real time demand on a per category or sub-category, per location or hyper-location, and per price range basis.

16. The apparatus of claim 15 , wherein the first classification is generated by:

normalizing the user search data, supplying the normalized user search data to a classifying model as attribute data, wherein the classifying model is a trainable classifier adapted based on a training data set of exemplary data representing exemplary terms previously determined to be semantically related to particular categories.

17. The apparatus of claim 15 , wherein the at least one memory and the computer program code are further configured to, with the processor, cause the apparatus to:

calculate a predicted demand for at least one promotion tuple, for a specified time period, wherein the predicted demand is representative of an estimated number of units to be sold during the specified time period, and wherein the promotion tuple comprises information indicative of a category or sub-category, a location, and a price range,

wherein the predicted demand is calculated by:

generating a virtual promotion, wherein the virtual promotion comprises a combination of a category or sub-category, a location, and a price range;

calculating a probability that a particular consumer would buy the virtual offer in a predetermined time period, wherein the probability is generated at least based on historical data related to the particular consumer and one or more related consumers;

determining an estimated number of units to be sold for the virtual offer as a function of at least the probability, the estimated number of units representing the predicted demand.

18. The apparatus of claim 15 , wherein the calculation of the real-time demand further comprises:

identifying a benchmark conversion rate;

comparing the real time demand to the benchmark conversion rate to set a modified real time demand that identifies a quantity of units that would have been purchased had the units been available;

identifying an actual purchase quantity; and

modifying the real time demand, wherein the real time demand is equal to the actual purchase quantity subtracted from the modified real time demand.

19. The apparatus of claim 17 , wherein the calculation of the real-time demand further comprises:

determining, via the processor, a total demand, on a per category or sub-category, per location or hyper-location, and per price range basis by summing the predicted demand and the real time demand.

20. The apparatus of claim 15 , wherein the first classification is derived from captured browsing activity and text input and the second classification is derived from any of global positioning system (GPS) data indicative of a location from the user device, character input indicative of the location of the user device, or profile data associated with the user device indicative of the location of the user device.

21. The apparatus of claim 15 , wherein the distribution of the real-time demand among the multiple hyper-locations, multiple sub-categories, and multiple price points is performed in accordance with a current distribution of units among the multiple hyper-locations, the multiple sub-categories, and the multiple price points within the high level location and the category or sub-category.