COMBINED ESTIMATE CONTEST AND PREDICTION MARKET

• US 20090076974A1
• Filed: 09/13/2007
• Published: 03/19/2009
• Est. Priority Date: 09/13/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: PROEBSTING, TODD A., BERG, HENRY G.
• Granted Patent: US 8,229,824 B2
• Time in Patent Office: Days
• US Class Current: 705/36.R
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• 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

Users participate in an estimate contest and a prediction market for forecasting an outcome of a future event. Data from the estimate contest and the prediction market can be combined to obtain accurate information about overall group beliefs and individual or sub-groups beliefs. In the estimate contest, users provide estimated probabilities of occurrence for different possible outcomes of the event. Trades can be proposed, or automatically executed, based on differences between the user'"'"'s estimated probabilities and probabilities obtained from a prediction market in which the user can buy and sell securities which represent the different outcomes. For example, a buying opportunity may be present when the user'"'"'s estimated probability exceeds the prediction market'"'"'s probability. Further, the user can express a risk level which is factored into the proposed trades.

Claims

1. A computer-implemented method for forecasting an event, comprising:

receiving a user input, via a user interface, of estimated probabilities of occurrence of different possible outcomes of an event;

determining one or more proposed trades in a prediction market based on the user'"'"'s estimated probabilities; and

providing an output, via the user interface, which depicts the one or more proposed trades.

2. The computer-implemented method of claim 1, further comprising:

determining, from the prediction market, probabilities of occurrence of the different possible outcomes of the event; and

identifying differences between the user'"'"'s estimated probabilities and the prediction market'"'"'s probabilities, the one or more proposed trades are determined based on the differences.

3. The computer-implemented method of claim 1, wherein:

the one or more proposed trades includes a trade regarding a security which represents one of the outcomes for which the user'"'"'s estimated probability exceeds the prediction market'"'"'s probability.

4. The computer-implemented method of claim 1, wherein:

the one or more proposed trades includes a trade regarding a security which represents one of the outcomes for which the user'"'"'s estimated probability is highest among the user'"'"'s estimated probabilities.

5. The computer-implemented method of claim 1, further comprising:

receiving an input from the user, via the user interface, indicating a risk profile of the user, wherein the one or more proposed trades are determined based on the risk profile.

6. The computer-implemented method of claim 5, wherein:

the risk profile is risk averse and the one or more proposed trades includes trades for a plurality of outcomes of the different possible outcomes which yield equal returns.

7. The computer-implemented method of claim 5, wherein:

the risk profile is risk seeking and the one or more proposed trades favor riskier trades.

8. The computer-implemented method of claim 1, further comprising:

receiving a user command, via the user interface, for executing at least one trade of the one or more proposed trades.

9. The computer-implemented method of claim 1, further comprising:

automatically executing at least one trade of the one or more proposed trades.

10. The computer-implemented method of claim 1, wherein:

the user'"'"'s estimated probabilities of occurrence of different possible outcomes of the event are received in an estimate contest.

11. A computer-implemented method for forecasting an event, comprising:

obtaining estimated probabilities of occurrence of different possible outcomes of an event from user inputs in an estimate contest;

obtaining probabilities of occurrence of the different possible outcomes of the event based on securities in a prediction market; and

reporting based on the estimated probabilities of occurrence from the estimate contest and the probabilities of occurrence from the prediction market.

12. The computer-implemented method of claim 11, wherein:

the reporting comprises providing a comparison of the estimated probabilities of occurrence from the estimate contest for at least one subset of the users in the estimate contest to the probabilities of occurrence from the prediction market, the at least one subset of the users including less than all users in the estimate contest.

13. The computer-implemented method of claim 11, wherein:

the reporting comprises providing a comparison of the estimated probabilities of occurrence from the estimate contest for at least one of the users in the estimate contest to the probabilities of occurrence from the prediction market.

14. The computer-implemented method of claim 11, wherein:

the reporting comprises identifying the estimated probabilities of occurrence from the estimate contest for at least one subset of users in the estimate contest, the at least one subset of users includes less than all users in the estimate contest.

15. The computer-implemented method of claim 11, wherein:

the probabilities of occurrence from the prediction market are based on prices and payoffs of the securities.

16. Computer readable media having computer readable software embodied thereon for programming at least one processor to perform a method, the method comprising:

receiving a user input, via a user interface, regarding estimated probabilities of occurrence of different possible outcomes of an event, and regarding a risk level;

determining one or more proposed trades in a prediction market based on the user'"'"'s estimated probabilities and risk level; and

providing an output, via the user interface, which depicts the one or more proposed trades.

17. The computer readable media of claim 16, wherein the method performed further includes:

determining, from the prediction market, probabilities of occurrence of the different possible outcomes of the event; and

identifying differences between the user'"'"'s estimated probabilities and the prediction market'"'"'s probabilities, the one or more proposed trades are determined based on the differences.

18. The computer readable media of claim 17, wherein:

the probabilities of occurrence determined from the prediction market are determined, for each of the different possible outcomes of the event, based on a corresponding cost of a bet and a payoff of the bet in the prediction market.

19. The computer readable media of claim 16, wherein:

the one or more proposed trades are designed to maximize an expected value for the user in the prediction market at a given time.

20. The computer readable media of claim 16, wherein:

the one or more proposed trades are designed to maximize an expected value for the user in the prediction market over different times.