Security analyst estimates performance viewing system and method

• US 7,149,716 B2
• Filed: 10/22/2001
• Issued: 12/12/2006
• Est. Priority Date: 04/24/1998
• Status: Expired due to Term

• Current Assignee: Refinitiv US Organization, LLC (Refinitiv US Holdings, Inc.)
• Original Assignee: StarMine Corp. (The Woodbridge Co. Ltd.)
• Inventors: Gatto, Joseph G.
• Primary Examiner(s): Kazimi, Hani M.
• Assistant Examiner(s): Subramanian, Narayanswamy
• Application Number:
  US09/982,838
• Publication Number:
  US 20020052820A1
• Time in Patent Office: 1,877 Days
• Field of Search: 705 35- 37, 707/101
• US Class Current: 705/36.00R
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

A system and method for measuring, analyzing, and tracking the past performance of security analysts'"'"' earnings estimates and recommendations. The present invention provides a database of historical data relating to security analyst earnings estimate predictions wherein a historical model enables users to view the historical data as a time series of earnings estimates for each analyst selected, for a selected period of time, for a predetermined earnings event. Users may define a model to automatically create enhanced composite estimates wherein an improved prediction of the quantity being estimated, such as company earnings, revenue or cash flow is obtained. Users may view performance screens and historical performance data for a particular contributor or various contributors for a given security. Other views may be available.

Claims

1. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, on one or more given days, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event on a given day relative to the average accuracy of the estimates for analysts having estimates for the event on the given day, wherein generating the relative accuracy score for each analyst further comprises providing a numerator that compares an analyst'"'"'s error on the given day with the average analyst error on that day, wherein the numerator comprises the difference between an analyst'"'"'s absolute error in an estimate and the average absolute error among a plurality of analysts'"'"' estimates, and providing a denominator that normalizes the numerator; and

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events.

2. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, on one or more given days, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event on a given day relative to the average accuracy of the estimates for analysts having estimates for the event on the given day, wherein generating the relative accuracy score for each analyst further comprises providing a numerator that compares an analyst'"'"'s error on the given day with the average analyst error on that day, and providing a denominator that normalizes the numerator, wherein the denominator comprises a function of a plurality of values to ensure that the relative accuracy score is normalized in proportion to a plurality of factors to meaningfully compare relative accuracy scores; and

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events.

3. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, on one or more given days, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event on a given day relative to the average accuracy of the estimates for analysts having estimates for the event on the given day, wherein generating the relative accuracy score for each analyst further comprises providing a numerator that compares an analyst'"'"'s error on the given day with the average analyst error on that day, and providing a denominator that normalizes the numerator, wherein normalization comprises normalizing the relative accuracy score around a neutral value; and

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events.

4. The method of claim 3, wherein the neutral value corresponds to the average absolute error among a number of analysts.

5. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, at one or more points in time, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event at a point in time relative to the average accuracy of the estimates for analysts having estimates for the event at that point in time;

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events; and

aggregating the relative accuracy score for an analyst over more than one point in time for a period of time, for a single event, to generate an analyst event score.

6. The method of claim 5, further comprising, if an analyst does not have an estimate for a given point in time in the period of time, assigning a central relative accuracy score for that analyst for that point in time.

7. The method of claim 5, wherein an analyst event score is capped within a range to enable more meaningful comparison with other analyst event scores.

8. The method of claim 5, wherein a point in time comprises a day, and further comprising determining a relative accuracy score for each day over a number of days prior to an event report and taking a weighted average of daily relative accuracy scores for an analyst to generate an aggregated relative accuracy score for the analyst for the event.

9. The method of claim 8, wherein when an estimate is not available or a relative accuracy score is not meaningfully calculable on a given day, replacing that day'"'"'s value with a neutral value.

10. The method of claim 9, wherein the neutral value is a value about which the relative accuracy scores are normalized.

11. The method of claim 8, wherein the weighting is equal for each day.

12. The method of claim 8, wherein the weighting for some days is greater than other days.

13. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, at one or more points in time, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event at a point in time relative to the average accuracy of the estimates for analysts having estimates for the event at that point in time;

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events; and

aggregating multiple relative accuracy scores for one analyst for one security for multiple events.

14. The method of claim 13, further comprising multiplying the aggregated relative accuracy score less a neutral value by an inflation factor then adding back the neutral value.

15. The method of claim 13, wherein the relative accuracy scores for events are truncated to lie within a predetermined range.

16. The method of claim 13, further comprising:

selecting a number (N) of single events for which there are relative accuracy scores to be aggregated;

taking the average (A) of the single event relative accuracy scores over the (N) events;

taking the difference between the average (A) and a neutral value for a range;

multiplying the difference (D) by a function f(n); and

adding the neutral value to the multiplied difference.

17. The method of claim 16, wherein the function f(n) comprises multiplying by a root of N.

18. The method of claim 16, wherein the function f(n) comprises multiplying by the square root of N.

19. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, on one or more given days, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event on a given day relative to the average accuracy of the estimates for analysts having estimates for the event on the given day, wherein generating the relative accuracy score for each analyst further comprises providing a numerator that compares an analyst'"'"'s error on the given day with the average analyst error on that day, and providing a denominator that normalizes the numerator, wherein the denominator is determined by selecting a maximum value from a plurality of values; and

generating individual relative accuracy ratings for each of the multiple analysts, for one or more events.

20. The method of claim 19, wherein the plurality of values comprises a number based on the standard deviation of analysts'"'"' estimates on a day.

21. The method of claim 19, wherein the plurality of values comprises a number based on the average absolute error of analysts on a day.

22. The method of claim 19, wherein the plurality of values comprises a number based on the absolute value of the actual event value.

23. The method of claim 19, wherein the plurality of values comprises a constant monetary value.

24. A computer-implemented method for measuring the relative accuracy of multiple analysts'"'"' estimates at one or more points in time for one or more events, the method comprising:

generating, for each of the multiple analysts, for one or more events, at one or more points in time, a relative accuracy score by comparing the accuracy of an analyst'"'"'s estimate for an event at a point in time relative to the average accuracy of the estimates for analysts having estimates for the event at that point in time; and

mapping relative accuracy scores to an accuracy rating system, wherein a relative accuracy score that falls within a predetermined range of relative accuracy scores is assigned an accuracy rating corresponding to that range, and the accuracy rating has corresponding symbols, where the number of symbols signifies the relative accuracy of an analyst.

25. The method of claim 24, where accuracy ratings range from 1–

5, and the symbols comprise stars.