System and method for analyzing analyst recommendations on a single stock basis

• US 7,877,309 B2
• Filed: 10/18/2004
• Issued: 01/25/2011
• Est. Priority Date: 10/18/2004
• Status: Active Grant

• Current Assignee: Refinitiv US Organization, LLC (Refinitiv US Holdings, Inc.)
• Original Assignee: StarMine Corp. (The Woodbridge Co. Ltd.)
• Inventors: Gatto, Joseph G., Lichtblau, David, McNeil, Iain, Jha, Vinesh
• Primary Examiner(s): Kalinowski; Alexander
• Assistant Examiner(s): Vyas; Abhishek
• Application Number:
  US10/965,720
• Publication Number:
  US 20060085247A1
• Time in Patent Office: 2,290 Days
• Field of Search: 705/36, 705 10- 11, 705/35, 705 37- 40
• US Class Current: 705/36.00R
• CPC Class Codes: G06Q 10/06393 Score-carding, benchmarking or key performance indicator [KPI] analysis
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• 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 and creating a score for the performance of one or more contributor recommendations on a single stock. According to one embodiment, the score may be derived via a payoff function that depends on a variety of factors. For example, the factors may include one or more of: i) the performance of the stock; ii) the performance of a selected benchmark; iii) the recommendation of the contributor for the stock; and/or iv) other factors. According to one embodiment the payoff function may be designed such that certain desired characteristics are satisfied.

Claims

1. A computer-implemented method of scoring at least one contributor for the performance of the contributor'"'"'s recommendation with respect to a single stock, the method comprising:

receiving, at a server, a user selection of a contributor from among a plurality of contributors;

receiving, at the server, a user selection of a stock from among a plurality of stocks;

executing a computer software program on the server to create a score for the contributor'"'"'s recommendation on the stock relative to a benchmark, the score being determined based on a payoff function that determines the score as a function of a plurality of factors, the factors comprising;

i) a benchmark-relative return on the stock, wherein the benchmark-relative return of the stock is a return on the stock relative to a return on a benchmark that corresponds to the stock; and

ii) the recommendation made by the contributor;

wherein the payoff function for a neutral recommendation on the stock has a maximum score at a baseline benchmark-relative return, and

wherein, for a single benchmark-relative return on the stock equal to the baseline benchmark-relative return, the score for a neutral recommendation determined according to the payoff function is greater than both the score determined according to the payoff function for a positive recommendation on the stock and the score determined according to the payoff function for a negative recommendation on the stock; and

storing the score in one or more electronic storage media associated with the server.

2. The method of claim 1 wherein the recommendation has been selected by the contributor from a group of at least three types of recommendations, including a positive recommendation, a neutral recommendation and a negative recommendation, and wherein the payoff function for the positive recommendation is a function having a positive slope with respect to the benchmark-relative return and the payoff function for the negative recommendation is a function having a negative slope with respect to the benchmark-relative return.

3. The method of claim 1 wherein the recommendation has been selected by the contributor from a group of at least five types of recommendations, including a positive recommendation, a more positive recommendation, a neutral recommendation, a negative recommendation and a more negative recommendation, and wherein the payoff function for the positive recommendation is a function having a first positive slope with respect to benchmark-relative return and a first positive function baseline value at the baseline benchmark-relative return, the payoff function for the more positive recommendation is a function having a second positive slope with respect to benchmark-relative return greater than the first positive slope and a second positive function baseline value that is offset in a positive direction from the first positive function baseline value along a benchmark-relative return axis, the payoff function for the negative recommendation is a function having a first negative slope with respect to benchmark-relative return and a first negative function baseline value at the baseline benchmark-relative return, and the payoff function for the more negative recommendation is a function having a second negative slope with respect to benchmark-relative return more negative than the first negative slope and a second negative baseline value that is offset in a negative direction from the first negative function baseline value along the benchmark-relative return axis.

4. The method of claim 1, wherein the baseline benchmark-relative return is zero.

5. The method of claim 1, wherein the benchmark includes a variable benchmark, including one of a sector benchmark, an industry benchmark, a geographic benchmark or a coverage benchmark.

6. The method of claim 1, wherein the contributor is an analyst, and the analyst is associated with a broker and the benchmark comprises a broker-specific benchmark.

7. The method of claim 1, wherein the contributor is an analyst, and the analyst is associated with a broker and where different brokers may associate recommendations with different numerical scales, the method further comprising the step of standardizing a recommendation to a common numerical scale.

8. The method of claim 1, further comprising implementing the computer software program on the server to normalize the score for the contributor'"'"'s recommendation for the stock.

9. The method of claim 1, further comprising implementing the computer software program on the server to normalize the score for the contributor'"'"'s recommendation for the stock based on the volatility of the stock.

10. The method of claim 1, further comprising implementing the computer software program on the server to aggregate the score for the contributor'"'"'s recommendation for the stock with one or more other scores for recommendations made by the contributor on the stock to create a stock-level score, implementing the computer software program on the server to normalize the stock-level score to create a normalized stock-level score, and implementing the computer software program on the server to create a stock set-level score by combining the normalized stock-level score with at least one other normalized stock-level score for recommendations made on another stock.

11. The method of claim 1, wherein a score is based at least in part on a period of time and further comprising implementing the computer software program on the server to adjust an contributor'"'"'s score if the contributor'"'"'s recommendation covers only a portion of the period of time.

12. A system for scoring at least one contributor for the performance of the contributor'"'"'s recommendation with respect to a single stock, the score for the recommendation depending on a plurality of factors, including the performance of the stock, the performance of a benchmark and the recommendation made by the contributor, the system comprising:

a server configured to access, over a network, one or more electronic storage media storing information relating to stock performance, benchmark performance and contributor'"'"'s recommendations;

an interface module implemented on the server through the execution of a computer software program, the interface module being configured to enable the server to receive selections of a user input through a remote terminal of a contributor from a plurality of contributors and of a stock from a plurality of stocks; and

a processing section within the server configured to execute a computer software program to create a score for a recommendation of the selected contributor on the selected stock based on a payoff function, wherein the payoff function for a neutral recommendation on the stock has a maximum in score at a baseline benchmark-relative return on the stock, wherein the benchmark-relative return on the stock is a return on the stock relative to a return on a benchmark that corresponds to the stock, and

wherein, for a single benchmark-relative return on the stock equal to the baseline benchmark-relative return, the score for a neutral recommendation determined according to the payoff function is greater than both of the score determined according to the payoff function for a positive recommendation on the stock and the score determined according to the payoff function for a negative recommendation on the stock.

13. The system of claim 12 wherein the recommendation is selected by the contributor from a group of at least three types of recommendations, including a positive recommendation, a neutral recommendation and a negative recommendation, and wherein the payoff function for the positive recommendation is a function having a positive slope with respect to benchmark-relative return and the payoff function for the negative recommendation is a function having a negative slope with respect to benchmark-relative return.

14. The system of claim 12 wherein the recommendation is selected by the contributor from a group of at least five types of recommendations, including a positive recommendation, a more positive recommendation, a neutral recommendation, a negative recommendation and a more negative recommendation, and wherein the payoff function for the positive recommendation is a function having a first positive slope with respect to benchmark relative return and a first positive function baseline value at the baseline benchmark-relative return, the payoff function for the more positive recommendation is a function having a second positive slope with respect to benchmark relative return greater than the first positive slope and a second positive function baseline value that is offset in a positive direction from the first positive function baseline value along a benchmark-relative return axis, the payoff function for the negative recommendation is a function having a first negative slope with respect to benchmark relative return and a first negative function baseline value at the baseline percent benchmark-relative return, and the payoff function for the more negative recommendation is a function having a second negative slope with respect to benchmark relative return more negative than the first negative slope and a second negative baseline value that is offset in a negative direction from the first negative function baseline value along the benchmark-relative return axis.

15. The system of claim 12, wherein the benchmark includes a fixed benchmark or a variable benchmark.

16. The system of claim 12, wherein the baseline benchmark-relative return is zero.

17. The system of claim 12, wherein the contributor is an analyst, and the analyst is associated with a broker and the benchmark comprises a broker-specific benchmark.

18. The system of claim 12, wherein the contributor is an analyst, and the analyst is associated with a broker and where different brokers may associate recommendations with different numerical scales, the processor further being operable to standardize a recommendation to a common numerical scale.

19. The system of claim 12, wherein the processing section within the server is configured to execute the computer software program to normalize the score for the contributor'"'"'s recommendation for the stock.

20. The system of claim 12, wherein the processing section within the server is configured to execute the computer software program to normalize the score for the contributor'"'"'s recommendation for the stock based on the volatility of the stock.

21. The system of claim 12, wherein the processing section within the server is configured to execute the computer software program to aggregate the score for the contributor'"'"'s recommendation for the stock with one or more other scores for recommendations made by the contributor on the stock to create a stock-level score, to normalize the stock-level score to create a normalized stock-level score, and to create a stock set-level score by combining the normalized stock-level score with at least one other normalized stock-level score for recommendations made on another stock.

22. The system of claim 12, wherein a score is based at least in part on a period of time and further wherein the processing section within the server is configured to execute the computer software program to adjust an contributor'"'"'s score if the contributor'"'"'s recommendation covers only a portion of the period of time.

23. The system of claim 12, wherein the processing section within the server is configured to execute the computer software program to generate a display conveying the score.