Self-learning valuation
A method of valuating a plurality of digital content items including: receiving the plurality of digital content items; for each received content item; establishing a plurality of attributes from content and characteristics of the content item; establishing a lifetime indicating a span of consumers interest in the content item; producing a valuation function for calculating a market value of the content item during its lifetime by finding and ranking nearest one or more previously processed content items having the plurality of attributes with closest similarity to the plurality of attributes of the received content item, performing weighted averaging of the valuation functions produced for the nearest one or more of the previously processed content items; and adapting, using “edge cutting” adaptation, the produced valuation function to a market response reflecting behavior of the consumers in response to the market values of the content item calculated by the valuation function.
1 . A method, comprising:
receiving, by a processor, a plurality of digital content items over a network or from a database, wherein each digital content item comprises metadata and data;
for each received content item:
analyzing, by a text processor executing on the processor, content of the received content item to identify keywords and ascertain significance of the identified keywords;
transforming, by the processor, the identified keywords into a vector of numeric attribute representations, wherein the vector of numeric attribute representations expresses a class or domain of the received content item;
defining, by the processor, a valuation function for determining a market value of the received content item, wherein the market value determined by the valuation function is based on the plurality of numeric attribute representations in the vector, and defining the valuation function comprises:
constructing, by a similarity modeler executing on the processor, a similarity model for the received content item based on the vector of numeric attribute representations;
finding and ranking, using the constructed similarity model, one or more previously processed content items having a plurality of numeric attribute representations with closest similarity to the plurality of numeric attribute representations of the received content item; and
performing averaging of valuation functions associated with the nearest one or more of the previously processed and ranked content items;
determining, by the processor, a market response reflecting behavior of one or more consumers based on online accesses of the plurality of digital content items by the one or more consumers;
adapting, by the processor, the defined valuation function according to the determined market response for continually correcting the market values of the plurality of digital content items by learning from the determined market response, using an edge-cutting adaptation method wherein the market values are dynamically varying based on the continual correction and are streamed along with the plurality of digital content items in real-time to the one or more consumers over the network; and
updating and streaming continually, by the processor, the market values of the plurality of digital content items with dynamically varying market values.
2 . The method of claim 1 , wherein each of the plurality of digital content items comprises metadata and data including one or more from a group of text, audio, video, and images.
3 . The method of claim 1 , wherein the plurality of attributes is used to express a class or domain of the received content item.
4 . The method of claim 1 , further comprising forming, by the processor, similarity models for each of the plurality of digital content items to enable identifying and ranking similar of the plurality of digital content items.
5 . The method of claim 1 , further comprising:
formulating, by an application on a device of a consumer, a code snippet based on content distribution requirements of a content distributor provided to the application, wherein the code snippet is custom crafted for a website of the content distributor in accordance with the content distribution requirements and maintained by the processor in a library, and wherein the code snippet is for placement on the website of the content distributor for distribution to one or more browsers of one or more devices of the one or more consumers; and
securely supporting and delivering, by the processor, the code snippet to external applications running on the one or more devices of the one or more consumers, wherein the external applications are executed by the one or more consumers by using network browsing programs on the one or more devices for performing one or more activities.
6 . The method of claim 5 , wherein the one or more activities include at least an activity related to an online registration, an activity related to a purchase of credit, an activity related to authoring of digital content items for adding to a content database, or an activity related to a purchase of access to one of the plurality of digital content items by using the purchased credit.
7 . The method of claim 1 , further comprising displaying the plurality of digital content items along with their market values on one or more devices of the one or more consumers.
8 . A system, comprising: a processor configured to:
receive a plurality of digital content items over a network or from a database, wherein each digital content item comprises metadata and data;
for each received content item:
analyze, via a text processor, content of the received content item to identify keywords and ascertain significance of the identified keywords;
transform the identified keywords into a vector of numeric attribute representations, wherein the vector of numeric attribute representations expresses a class or domain of the received content item;
define a valuation function for determining a market value of the received content item, wherein the market value determined by the valuation function is based on the plurality of numeric attribute representations in the vector, and defining the valuation function comprises:
construct, via a similarity modeler, a similarity model for the received content item based on the vector of numeric attribute representations;
find and rank, using the constructed similarity model, one or more previously processed content items having a plurality of numeric attribute representations with closest similarity to the plurality of numeric attribute representations of the received content item; and
perform averaging of valuation functions associated with the nearest one or more of the previously processed and ranked content items;
determine a market response reflecting behavior of one or more consumers based on online accesses of the plurality of digital content items by the one or more consumers;
adapt the defined valuation function according to the determined market response for continually correcting the market values of the plurality of digital content items by learning from the determined market response using an edge-cutting adaptation method, wherein the market values are dynamically varying based on the continual correction and are streamed along with the plurality of digital content items in real-time to the one or more consumers over the network; and
update and stream continually the market values of the plurality of digital content items with dynamically varying market values.
9 . The system of claim 8 , wherein each of the plurality of digital content items comprises metadata and data including one or more from a group of text, audio, video, and images.
10 . The system of claim 8 , wherein the plurality of attributes is used to express a class or domain of the received content item.
11 . The system of claim 8 , wherein the processor is further configured to form similarity models for each of the plurality of digital content items to enable identifying and ranking similar of the plurality of digital content items.
12 . The system of claim 8 , wherein:
the system includes a device of a consumer including a device processor with an application configured to formulate a code snippet based on content distribution requirements of a content distributor provided to the application, wherein the code snippet is custom crafted for a website of the content distributor in accordance with the content distribution requirements and maintained by the processor of the system in a library, and wherein the code snippet is for placement on the website of the content distributor for distribution to one or more browsers of one or more devices of the one or more consumers; and
the processor of the system is further configured to securely support and deliver the code snippet to external applications running on the one or more devices of the one or more consumers, wherein the external applications are executed by the one or more consumers by using network browsing programs on the one or more devices for performing one or more activities.
13 . The system of claim 12 , wherein the one or more activities include at least an activity related to an online registration, an activity related to a purchase of credit, an activity related to authoring of digital content items for adding to a content database, or an activity related to a purchase of access to one of the plurality of digital content items by using the purchased credit.
14 . The system of claim 8 , wherein the processor is further configured to display the plurality of digital content items along with their market values on one or more devices of the one or more consumers.
15 . A non-transitory computer-readable medium having computer readable program code embodied thereon, the computer-readable program code, when executed by a processor, causes the processor to perform:
receiving a plurality of digital content items over a network or from a database, wherein each digital content item comprises metadata and data;
for each received content item:
analyzing, via a text processor, content of the received content item to identify keywords and ascertain significance of the identified keywords;
transforming the identified keywords into a vector of numeric attribute representations, wherein the vector of numeric attribute representations expresses a class or domain of the received content item;
defining a valuation function for determining a market value of the received content item, wherein the market value determined by the valuation function is based on the plurality of numeric attribute representations in the vector, and defining the valuation function comprises:
constructing, via a similarity modeler, a similarity model for the received content item based on the vector of numeric attribute representations;
finding and ranking, using the constructed similarity model, one or more previously processed content items having a plurality of numeric attribute representations with closest similarity to the plurality of numeric attribute representations of the received content item, and;
performing averaging of valuation functions associated with the nearest one or more of the previously processed and ranked content items;
determining a market response reflecting behavior of one or more consumers based on online accesses of the plurality of digital content items by the one or more consumers;
adapting the defined valuation function according to the determined market response for continually correcting the market values of the plurality of digital content items by learning from the determined market response using an edge-cutting adaptation method, wherein the market values are dynamically varying based on the continual correction and are streamed along with the plurality of digital content items in real-time to the one or more consumers over the network; and
updating and streaming continually the market values of the plurality of digital content items with dynamically varying market values.
16 . The non-transitory computer-readable medium of claim 15 , wherein each of the plurality of digital content items comprises metadata and data including one or more from a group of text, audio, video, and images.
17 . The non-transitory computer-readable medium of claim 15 , wherein the computer-readable program code further causes the processor to form similarity models for each of the plurality of digital content items to enable identifying and ranking similar of the plurality of digital content items.
18 . The non-transitory computer-readable medium of claim 15 , further comprising computer-readable program code for:
formulating, by an application on a device of a consumer, a code snippet based on content distribution requirements of a content distributor provided to the application, wherein the code snippet is custom crafted for a website of the content distributor in accordance with the content distribution requirements and maintained by the processor in a library, and wherein the code snippet is for placement on the website of the content distributor for distribution to one or more browsers of one or more devices of the one or more consumers; and
securely supporting and delivering the code snippet to external applications running on the one or more devices of the one or more consumers, wherein the external applications are executed by the one or more consumers by using network browsing programs on the one or more devices for performing one or more activities.
19 . The non-transitory computer-readable medium of claim 18 , wherein the one or more activities include at least an activity related to an online registration, an activity related to a purchase of credit, an activity related to authoring of digital content items for adding to a content database, or an activity related to a purchase of access to one of the plurality of digital content items by using the purchased credit.
20 . The non-transitory computer-readable medium of claim 15 , wherein the plurality of attributes is used to express a class or domain of the received content item.