Machine generated financial summary
The present disclosure is directed towards systems and methods for generating a financial summary, which comprises identifying a first set of data items derived from one or more financial documents associated with an entity and a second set of data items derived from historical data associated with the entity. The systems and methods of the present disclosure then compare one or more data items of each set of data and select selecting a pre-defined reporting pattern based on the comparison, the selected pre-defined reporting pattern indicative of a possible financial result of the entity. A third set of data items supporting the selected pre-defined reporting pattern is then generated from the first and second sets of data items and a financial summary of the one or more financial documents is computed using the selected pre-defined reporting pattern and the third set of data items.
1. A computer-implemented method of automatically summarizing one or more financial documents to provide automated analysis of an entity, the method comprising:
obtaining, by a processor, a set of rules that define string outputs as a function of variables tagged from the one or more financial documents and requirements to analyze the variables;
parsing, by the processor, a first set of data items derived from the one or more financial documents and comprising values for one or more of the variables;
determining, by the processor, a second set of data items derived from historical data associated with the entity, said determining further comprises accessing historical financial information maintained in a fundamentals database, the fundamentals database further comprising structured and unstructured documents;
comparing, by the processor, one or more data items of the first set of data items to one or more data items of the second set of data items to determine whether there is a change detected in net income or revenue for the entity;
selecting, by the processor, a pre-defined reporting pattern from a set of pre-defined reporting patterns based on the change detected by the comparison, the set of pre-defined reporting patterns maintained in a structured data store comprising at least a set of pre-defined business case scenarios, the selected pre-defined reporting pattern indicative of a possible financial result of the entity, the pre-defined reporting pattern further defines requirements to identify reasons attributed to the change detected;
generating, by the processor, using the set of rules, a set of strings comprising a third set of data items supporting the selection of the pre-defined reporting pattern, wherein the supporting provides for reasoning based on analytics relating to the selection, wherein the third set of data items comprises one or more reasons attributed to the change detected, one or more data items of the first set of data items and the second set of data items, and one or more delta values between data items of the first set of data items and the second set of data items, each string in the set of string representing different aspects of the financial summary to be generated;
assembling, by the processor, the set of strings to generate a final string;
automatically generating, by the processor, the financial summary of the one or more financial documents based on the final string;
generating, by the processor, a signal associated with the financial summary; and
transmitting, by the processor, the signal to an access device in response to a request for the financial summary.
2. The computer-implemented method of claim 1 , wherein the first, second and third set of data items comprise numeric data items and textual data items.
3. The computer-implemented method of claim 1 , wherein the first set of data items comprises one or more data items for a given reporting time period.
4. The computer-implemented method of claim 3 , wherein the second set of data items comprises one or more data items for one or more comparable prior time periods to the given reporting time period.
5. The computer-implemented method of claim 1 , wherein the first set of data items comprise a total revenue value and either a total net income value or a total net loss value and the second set of data items comprise a total revenue value and either a total net income value or a total net loss value.
6. The computer implemented method of claim 5 , wherein the first and second sets of data items further comprise at least one of the following: business segment revenue values, business segment net income values, geographic segment revenue values, geographic segment net income value, operating metrics, dividends per share and earnings per share.
7. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
8. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed increase in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
9. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
10. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed increase in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
11. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed increase in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
12. The computer-implemented method of claim 5 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed decrease in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
13. The computer-implemented method of claim 1 , wherein the financial summary further comprises an entity name and at least one of an industry value, a reporting period value, a reporting unit value, a currency type value, a currency exchange rate value, an accounting standard value and a consolidation basis value.
14. The method of claim 1 , wherein the set of rules comprises a first rule to generate a first string portion relating to the reasons attributed to the change detected, the method further comprising:
accessing at least a first variable from among the variables tagged from the one or more financial documents;
outputting the first string portion based on the first variable and the first rule.
15. The method of claim 14 , wherein outputting the first string portion comprises processing the first variable against a first rule comprising a condition used to identify plain language text to include in the first string portion.
16. The method of claim 15 , further wherein outputting the first string portion comprises:
selecting a template from among a plurality of templates based on the condition, wherein the template includes at least some of the plain language text.
17. A system for generating a financial summary, the system comprising:
a data repository comprising one or more financial documents, one or more items of historical data and one or more pre-defined reporting patterns; and
a server including a processor and memory storing instructions that, in response to receiving a request for access to a service, cause the processor to:
obtain a set of rules that define string outputs as a function of variables tagged from the one or more financial documents and requirements to analyze the variables;
identify a first set of data items parsed from the one or more financial documents associated with an entity;
identify a second set of data items derived from historical data associated with the entity, said identify further comprises accessing historical financial information maintained in a fundamentals database, the fundamentals database further comprising structured and unstructured documents;
compare one or more data items of the first set of data items to one or more data items of the second set of data items to determine whether there is a change detected in net income or revenue for the entity;
select a pre-defined reporting pattern from a set of pre-defined reporting patterns based on the change detected by the comparison, the set of pre-defined reporting patterns maintained in a structured data store comprising at least a set of pre-defined business case scenarios, the selected pre-defined reporting pattern indicative of a possible financial result of the entity, the pre-defined reporting pattern further defines requirements to identify reasons attributed to the change detected;
generate, using the set of rules, a set of strings comprising a third set of data items supporting the selection of the pre-defined reporting pattern, wherein the supporting provides for reasoning based on analytics relating to the selection, wherein the third set of data items comprises one or more reasons attributed to the change detected, one or more data items of the first set of data items and the second set of data items, and one or more delta values between data items of the first set of data items and the second set of data items, each string in the set of string representing different aspects of the financial summary to be generated;
assemble the set of strings to generate a final string;
automatically generate the financial summary of the one or more financial documents based on the final string;
generate a signal associated with the financial summary; and
transmit the signal to an access device in response to a request for the financial summary.
18. The system of claim 17 , wherein the first, second and third set of data items comprise numeric data items and textual data items.
19. The system of claim 17 , wherein the first set of data items comprises one or more data items for a given reporting time period.
20. The system of claim 19 , wherein the second set of data items comprises one or more data items for one or more comparable prior time periods to the given reporting time period.
21. The system of claim 17 , wherein the first set of data items comprise a total revenue value and either a total net income value or a total net loss value and the second set of data items comprise a total revenue value and either a total net income value or a total net loss value.
22. The system of claim 21 , wherein the first and second sets of data items further comprise at least one of the following: business segment revenue values, business segment net income values, geographic segment revenue values, geographic segment net income value, operating metrics, dividends per share and earnings per share.
23. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
24. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed increase in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
25. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
26. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed increase in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
27. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a negative reason to support an observed increase in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
28. The system of claim 21 , wherein the pre-defined reporting pattern comprises one or more instructions to identify a positive reason to support an observed decrease in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
29. The system of claim 17 , wherein the financial summary further comprises an entity name and at least one of an industry value, a reporting period value, a reporting unit value, a currency type value, a currency exchange rate value, an accounting standard value and a consolidation basis value.
30. Non-transitory computer readable media comprising program code stored thereon for execution by a programmable processor to perform a method for generating a financial summary, the program code causing the programmable processor to:
obtain a set of rules that define string outputs as a function of variables tagged from a financial document and requirements to analyze the variables;
identify a first set of data items derived from one or more financial documents associated with an entity and comprising values for one or more of the variables;
identify a second set of data items derived from historical data associated with the entity, said identifying further comprises accessing historical financial information maintained in a fundamentals database, the fundamentals database further comprising structured and unstructured documents;
compare one or more data items of the first set of data items to one or more data items of the second set of data items to determine whether there is a change detected in net income or revenue for the entity;
select a pre-defined reporting pattern from a set of pre-defined reporting patterns based on the change detected by the comparison, the set of pre-defined reporting patterns maintained in a structured data store comprising at least a set of pre-defined business case scenarios, the selected pre-defined reporting pattern indicative of a possible financial result of the entity, the pre-defined reporting pattern further defines requirements to identify reasons attributed to the change detected;
generate, using the set of rules, a set of strings based on a third set of data items supporting the selection of the pre-defined reporting pattern, wherein the supporting provides for reasoning based on analytics relating to the selection, wherein the third set of data items comprises one or more reasons attributed to the change detected, one or more data items of the first set of data items and the second set of data items, and one or more delta values between data items of the first set of data items and the second set of data items, each string in the set of string representing different aspects of the financial summary to be generated;
assemble the set of strings to generate a final string;
automatically generate the financial summary based on the final string;
generate a signal associated with the financial summary; and
transmit the signal to an access in response to a request for the financial summary.
31. The computer readable media of claim 30 , wherein the first, second, and third set of data items comprise numeric data items and textual data items.
32. The computer readable media of claim 30 , wherein the first set of data items comprises one or more data items for a given reporting time period.
33. The computer readable media of claim 32 , wherein the second set of data items comprises one or more data items for one or more comparable prior time periods to the given reporting time period.
34. The computer readable media of claim 30 , wherein the first set of data items comprise a total revenue value and either a total net income value or a total net loss value and the second set of data items comprise a total revenue value and either a total net income value or a total net loss value.
35. The computer readable media of claim 34 , wherein the first and second sets of data items further comprise at least one of the following: business segment revenue values, business segment net income values, geographic segment revenue values, geographic segment net income value, operating metrics, dividends per share and earnings per share.
36. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
37. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a positive reason to support an observed increase in the comparison of the total revenue value of the first set of data items and the total revenue value of the second set of data items.
38. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a negative reason to support an observed decrease in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
39. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a positive reason to support an observed increase in the comparison of the total net income value of the first set of data items and the total net income value of the second set of data items.
40. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a negative reason to support an observed increase in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
41. The computer readable media of claim 34 , wherein the pre-defined reporting pattern comprises program code comprising one or more instructions to identify a positive reason to support an observed decrease in the comparison of the total net loss value of the first set of data items and the total net loss value of the second set of data items.
42. The computer readable media of claim 30 , wherein the financial summary further comprises an entity name and at least one or an industry value, a reporting period value, a reporting unit value, a currency type value, a currency exchange rate value, an accounting standard value and a consolidation basis value.