US20110218045A1 - Predicting game player monetization based on player logs - Google Patents

Abstract

A massively multiplayer online game (MMOG) monetization analysis computer system may include an electronic data processing system configured to electronically analyze data, including player behavioral logs, in accordance with one or more algorithms. Based on the analysis, the electronic data processing system may predict player changes that are relevant to monetization of the MMOG and generate a report relating to these predicted changes. The analysis may identify players whom are predicted to terminate their subscriptions to the MMOG, an amount of time each of several players is likely to spend playing the MMOG, and/or a number of transactions each of a several players is likely to engage in while playing the MMOG.

Description

CROSS-REFERENCE TO RELATED APPLICATION
• This application is based upon and claims priority to U.S.provisional patent application 61/311,643, entitled “IDENTIFYING AND MITIGATING PLAYER CHURN IN MASSIVELY MULTIPLAYER ONLINE GAMES,” filed Mar. 8, 2010, attorney docket number 028080-0559. The entire content of this application is incorporated herein by reference.
STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH
• This invention was made with Government support under Contract Nos. PROJ0001352, awarded by the National Science Foundation, W91WAW-08-C-0106, Subaward No. SP003153 PROJ0001029, awarded by the Army Research Institute, and FA8650-10-C-7010, Subcontract Number 072933393, awarded by the Air Force Research Laboratory. The Government has certain rights in the invention.
BACKGROUND
• 1. Technical Field
• This disclosure relates to massively multiplayer online games (MMOGs), including predicting monetization from such games.
• 2. Description of Related Art
• MMOGs, such as massively multiplayer role-playing online games (MMORPGs), can generate revenue in a variety of ways, such as from subscription fees paid periodically by players, ad fees for advertisements displayed within the games, and/or transaction fees for transactions which take place during the games.
• When a player leaves a game or stops actively using it, however, revenue can be lost. However, predicting when this may occur and thus minimizing its occurrence can be difficult.
• Online game forums can be studied to gain information about aspects of a game that may need to be changed. However, the evidence which may be obtained from such a study may be anecdotal and incomplete.
• Surveys can also be sent to players after they have terminated their subscriptions. However, such surveys may not be practical for games which do not charge a subscription and, again, may only provide anecdotal and incomplete information.
SUMMARY
• A massively multiplayer online game (MMOG) monetization analysis computer system may include an electronic data processing system configured to electronically analyze data, including player behavioral logs, in accordance with one or more algorithms. Based on the analysis, the electronic data processing system may predict player changes that are relevant to monetization of the MMOG and generate a report relating to these predicted changes.
• The predicted player changes may be indicative of predicted changes by individual players.
• The electronic data processing system may be configured to extract from the player behavioral logs and to consider as part of the analysis longitudinal data indicative of player behavior over a period of time, cross-sectional cumulative data indicative of how frequently players perform the same type of activity, and/or social networking data indicative of player social networking while playing the MMOG.
• The electronic data processing system may be configured to consider as part of the analysis survey data indicative of the results of a survey of players and/or former players of the MMOG, game context data indicative of all or portions of the game context in which the data in the player behavioral logs took place, and/or commercial outcome data indicative of changes in player subscriptions to the MMOG.
• The analysis may identify players who are predicted to terminate their subscriptions to the MMOG, an amount of time each of several players is likely to spend playing the MMOG, and/or a number of transactions each of a several players is likely to engage in while playing the MMOG.
• The MMOG may be a massively multiplayer role-playing online game (MMRPOG).
• The MMOG may be modified to increase its monetization based on the predictions of the analysis.
• These, as well as other components, steps, features, objects, benefits, and advantages, will now become clear from a review of the following detailed description of illustrative embodiments, the accompanying drawings, and the claims.
BRIEF DESCRIPTION OF DRAWINGS
• The drawings are of illustrative embodiments. They do not illustrate all embodiments. Other embodiments may be used in addition or instead. Details which may be apparent or unnecessary may be omitted to save space or for more effective illustration. Some embodiments may be practiced with additional components or steps and/or without all of the components or steps which are illustrated. When the same numeral appears in different drawings, it refers to the same or like components or steps.
• FIG. 1 illustrates an example of a massively multiplayer online game (MMOG), associate players, player behavioral logs, various types of data, and a monetization analysis computer system and associated reporting device.
• FIG. 2 illustrates an example of the monetization analysis computer system illustrated inFIG. 1.
• FIG. 3 illustrates an example of a monetization enhancement process which may be performed using the monetization analysis computer system illustrated inFIG. 2.
• FIG. 4 is an example of a screen of a player-level report which may be generated by the monetization analysis computer system illustrated inFIG. 2.
• FIG. 5 is an example of a screen of an aggregate-level report which may be generated by the monetization analysis computer system illustrated inFIG. 2.
DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS
• Illustrative embodiments are now described. Other embodiments may be used in addition or instead. Details which may be apparent or unnecessary may be omitted to save space or for a more effective presentation. Some embodiments may be practiced with additional components or steps and/or without all of the components or steps which are described.
• FIG. 1 illustrates an example of a massively multiplayer online game (MMOG), associate players, player behavioral logs, various types of data, and a monetization analysis computer system and associated reporting device.
• As illustrated inFIG. 1, a number of players, such asplayers101,103, and105, may play a massively multiplayer online game (MMOG)107. The players may play the MMOG at the same or different times.
• TheMMOG107 may be any type of MMOG. For example, the MMOG may be a massively multiplayer role-playing online game (MMRPOG), such as World of Warcraft, EverQuest II, MapleStory, or Lord of the Rings Online.
• TheMMOG107 may be configured to generate playerbehavioral logs109. These logs may log the behavioral actions of each player while the player is playing theMMOG107. For each player, the logs may include information such as an identification of the player, the date and time when the player began playing theMMOG107, each behavioral action which the player took while playing theMMOG107, such as individual and group quests, monster kills, player deaths, in-game trade activities, spells cast, failures by individuals or groups, and/or player versus player interactions, and the time and date the player stopped playing theMMOG107. Activity during each time period may be stored in a separate log. Each log may be stored in a different file or one or more of the logs may be stored in the same file.
• A monetizationanalysis computer system111 may be configured to receive the data within the playerbehavioral logs109, as well assurvey data113,game context data115,commercial outcome data117, and/or other types of data. The monetizationanalysis computer system111 may be configured to predict player changes that are relevant to monetization of theMMOG107 based on an analysis of this data and to generate a report relating to these predicted changes.
• Thesurvey data113 may be indicative of the results of a survey of players and/or former players of theMMOG107. Thesurvey data113 may include demographic information and/or psychometric indicators.
• Thegame context data115 may be indicative of all or portions of the game context in which the data in the playerbehavioral logs109 took place. For example, thegame context data115 may include in-game location, nature and difficulty level of quest, and/or the overall game storyline.
• Thecommercial outcome data117 may be indicative of changes in player subscriptions to theMMOG107. For example, thecommercial outcome data117 may indicate which players have and have not continued their subscriptions and/or purchased items within the game.
• Amonetization reporting device119 may be configured to communicate the report generated by the monetizationanalysis computer system111 to one or more users. For example, themonetization reporting device119 may consist of or include a display, a printer, and/or another computing system.
• FIG. 2 illustrates an example of the monetization analysis computer system illustrated inFIG. 1. The monetization analysis computer system illustrated inFIG. 2 may be used in connection with a MMOG and related components which are different from the one illustrated inFIG. 1. Similarly, the monetizationanalysis computer system111 which is illustrated inFIG. 1 may be different from the one illustrated inFIG. 2.
• As illustrated inFIG. 2, the monetization analysis computer system may include adata input interface201, adata processing system203, adata output interface205, and data extracted from playerbehavioral logs207.
• Thedata input interface201 may be configured to electronically receive data relevant to the monetization of theMMOG107, including the playerbehavioral logs109, thesurvey data113, thegame context data115, thecommercial outcome data117, and/or other types of data. Thedata input interface201 may include a network interface card and/or any other type of data input interface.
• Thedata processing system203 may be configured to extract various types of data from the playerbehavioral logs109, such aslongitudinal data209, cross-sectionalcumulative data211, and/orsocial networking data213, all of which may be part of the data extracted from playerbehavioral logs207.
• Thelongitudinal data209 may be indicative of player behavior over a period of time. For example, thelongitudinal data209 may be indicative of the number of active sessions for the time period under consideration, the length of these sessions, and/or inactivity time between sessions. Thelongitudinal data209 may be indicative of player behavior in multiple categories, such as individual and group quests, trade, and/or player combat.
• The cross-sectional cumulative data may be indicative of how frequently the players perform the same type of activity. For example, the cross-sectional cumulative data may be indicative of how frequently and how many times players complete quests, send messages, level up within the game, and/or participate in group activities.
• Thesocial networking data213 may be indicative of players' social networking while playing theMMOG107. For example, thesocial networking data213 may be indicative of interactions between players, trades which players have made between themselves either while playing theMMOG107 or through a mail system which may be provided by theMMOG107, communications between players, voice and text messages which may be sent between players, and/or groups which players may have joined.
• The data extracted from playerbehavioral logs207 may be stored in any type of storage device, such as in one or more hard disk drives, CD's, DVD's, and/or flash memories.
• Thedata processing system203 may be configured to electronically analyze the data received by thedata input interface201, including the playerbehavioral logs109, thesurvey data113, thegame context data115, thecommercial outcome data117, and/or any other type of data, in accordance with one or more algorithms. The algorithms may be configured to predict player changes that are relevant to monetization of theMMOG107. Examples of these are discussed below. The electronicdata processing system203 may be configured to generate a report relating to these predicted changes.
• The predicted player changes may be indicative of predictive changes by individual players. For example, the predicted player changes may indicate which players are predicted to terminate their subscriptions to theMMOG107 within a time period, the amount of time each of several players is likely to spend playing theMMOG107 within a time period, and/or the number of transactions which each of several players is likely to engage in within theMMOG107 within a time period.
• Thedata output interface205 may be configured to electronically deliver the report which is generated by thedata processing system203 to an output device, such as to themonetization reporting device119. Thedata output interface205 may be of any type. For example, it may consist of or include a network interface card.
• FIG. 3 illustrates an example a monetization enhancement process which may be performed using the monetization analysis computer system illustrated inFIG. 2.
• As illustrated inFIG. 3, the various types of data which have been described above in connection withFIGS. 1 and/or2 may be analyzed for the purpose of predicting player changes which are relevant to monetization of the MMOG, as reflected by a Monetization Analysis ofData step301. Based on the results of this analysis, a report relating to these predicted changes may be generated, as reflected by a GenerateMonetization report303.
• This report may be analyzed for the purpose of determining what changes to theMMOG107 may be made to enhance monetization, following which these changes may be made, as reflected by an EnhanceMonetization step305.
• Any one or more algorithms may be used for the purpose of analyzing the various types of data which have been discussed for the purpose of predicting player changes that are relevant to monetization of theMMOG107. Examples are now discussed.
• Thedata processing system203 may take input from thedata input interface201 and extract features which are indicative of a player's level of motivation and engagement within the game. Examples of player motivational factors may include achievement, socialization and immersion, and various sub-factors within those factors. Using such features, thedata processing system203 may build a predictive model of player churn behavior. Given a player and the features extracted from the logs for the player, this predictive model may compute a churn probability for the player.
• Instead of building a single model as in the previous example, thedata processing system203 may first segment the players based on different criteria, such as average playtime and experience level. Thedata processing system203 may then build diverse, localized models for each of the segments and then combine their results to attain improved global performance. Whenever the churn probability of a player needs to be computed, the system would first find out the segment to which the player belongs and use the localized model for that segment to calculate the churn probability.
• The types of reports which are generated relating to these predicted changes may be of any type. For example, there may be an individual player-level report which provides each player's churn probability at any point of time, expected time for which the player will continue playing the game, and direct and indirect monetary impact in case the player leaves the game.
• In addition to the individual player-level reports described above, the reports may be at an aggregate level along different dimensions, including but not restricted to time, space, and different facets of player character and demographics.
• FIG. 4 is an example of a screen of a player-level report which may be generated by the monetization analysis computer system illustrated inFIG. 2. The monetization analysis computer system may generate a different player-level report and the player-level report which is illustrated inFIG. 4 may be generated by a different monetization analysis computer system.
• As illustrated inFIG. 4, the report may contain different monetary-related information for each player, such as the account number (“Account”), a date of account creation (“Creation Date”), an age of the account (“Account Age (days)”), the account (“Type”), an expected monetary loss in case the player leaves the game (“Expected Loss”), an identification of the algorithm used to predict churn probability (“Technique”), and the confidence of the model in making that prediction (“Confidence”).
• InFIG. 4, the graphs on the right may portray a selected player's churn probability (“Churn Probability”) at different times, the history of player level changes (“Leveling over Time”), and playing hours in the recent past (“Hours Played Over Time”). When an account is selected on the table at the left, the graphs on the right may change to reflect the information for that selected account.
• The “Type” of account may be based on likelihood that the account will churn, as predicted by the prediction model. The ‘type’ values may be labels constructed depending on range of churn probabilities. For example, if an account has a predicted churn probability above 90%, it could be labeled as ‘Likely to churn’ and so on.
• The “Expected Loss” may be based on the time a player is expected to continue playing the game multiplied by the subscription per unit of time. It may be just the expected value of the churn probability.
• As illustrated in [0048], the data processing system may build a collection of diverse, localized models for different player segments and depending on the segment a player belongs to, the appropriate model/algorithm would be used. The ‘Technique’ may refer to the particular localized model/algorithm used for the player. ‘Confidence’ may be the statistical confidence of the model in its decision.
• “Churn Probability” may be calculated by the model/technique which is being used as illustrated in [0047]
• “Leveling over Time” may be based on the longitudinal data in the player behavioral logs. This is a descriptive chart which shows how the player level changed over time.
• FIG. 5 is an example of a screen of an aggregate-level report which may be generated by the monetization analysis computer system illustrated inFIG. 2. The monetization analysis computer system may generate a different aggregate-level report and the player-level report which is illustrated inFIG. 4 may be generated by a different monetization analysis computer system.
• As illustrated inFIG. 5, the report may show the number of players that have churned in the past (“Churn over Time (Historical)”) and the number of players who are likely to churn in the near future (“Churn over Time (Projection)”). These results may be filtered by various criteria, such as player gender, ethnicity, and/or geographic location. The churn probabilities may be are calculated by the model selected for each account, and the account may have gender, ethnicity, and/or geographic location information associated with it. So, the aggregated reports may be along different dimensions.
• The screens inFIGS. 4 and 5 may be linked, enabling a user to drill-down from an aggregated data point inFIG. 5 to the table of players inFIG. 4 which contribute to that point. Similarly, the screens may be configured to enable a user to roll-up from individual churn probabilities of the accounts inFIG. 4 to get to an aggregated churn probability report inFIG. 5. In general, the monetization analysis computer system may be configured to provide different types of reports at different levels of granularity using an appropriate screen navigation system.
• TheMMOG107 and the MonetizationAnalysis Computer System111 and which have been discussed may each be implemented with a computer system configured to perform the functions which have been described herein for the component. Each computer system may include one or more computers at the same or different locations. When at different locations, the computers may be configured to communicate with one another through a wired and/or wireless network communication system. Each computer may include one or more processors, memory devices (e.g., random access memories (RAMs), read-only memories (ROMs), and/or programmable read only memories (PROMS)), tangible storage devices (e.g., hard disk drives, CD/DVD drives, and/or flash memories), system buses, video processing components, network communication components, input/output ports, and/or user interface devices (e.g., keyboards, pointing devices, displays, microphones, sound reproduction systems, and/or touch screens). Each computer may include software (e.g., one or more operating systems, device drivers, application programs, and/or communication programs), which may be configured when executed to cause the computer to perform one or more of the functions which have been described herein for the computer system. The software may include programming instructions and associated data and libraries. The software may implement one or more algorithms which may cause the computer to perform each function. The software may be stored on one or more tangible storage devices, such as one or more hard disk drives, CDs, DVDs, and/or flash memories. The software may be in source code and/or object code format. Associated data may be stored in any type of volatile and/or non-volatile memory.
• The components, steps, features, objects, benefits and advantages which have been discussed are merely illustrative. None of them, nor the discussions relating to them, are intended to limit the scope of protection in any way. Numerous other embodiments are also contemplated. These include embodiments which have fewer, additional, and/or different components, steps, features, objects, benefits and advantages. These also include embodiments in which the components and/or steps are arranged and/or ordered differently.
• For example, the monetization analysis computer system may offer its analytic functionalities as a web service which may be utilized by authenticated computer systems over a network. Such a service may be used by game companies as a back end to their own reporting tools.
• Some MMOGs may use different business models, such as free-to-play or prepaid. The type and nature of the monetization analysis which is performed for such games may vary in appropriate ways to match these different business models.
• Unless otherwise stated, all measurements, values, ratings, positions, magnitudes, sizes, and other specifications which are set forth in this specification, including in the claims which follow, are approximate, not exact. They are intended to have a reasonable range which is consistent with the functions to which they relate and with what is customary in the art to which they pertain.
• All articles, patents, patent applications, and other publications which have been cited in this disclosure are incorporated herein by reference.
• The phrase “means for” when used in a claim is intended to and should be interpreted to embrace the corresponding structures and materials which have been described and their equivalents. Similarly, the phrase “step for” when used in a claim is intended to and should be interpreted to embrace the corresponding acts which have been described and their equivalents. The absence of these phrases in a claim mean that the claim is not intended to and should not be interpreted to be limited to any of the corresponding structures, materials, or acts or to their equivalents.
• The scope of protection is limited solely by the claims which now follow. That scope is intended and should be interpreted to be as broad as is consistent with the ordinary meaning of the language which is used in the claims when interpreted in light of this specification and the prosecution history which follows and to encompass all structural and functional equivalents. Notwithstanding, none of the claims are intended to embrace subject matter which fails to satisfy the requirement ofSections 101, 102, or 103 of the Patent Act, nor should they be interpreted in such a way. Any unintended embracement of such subject matter is hereby disclaimed.
• Except as stated immediately above, nothing which has been stated or illustrated is intended or should be interpreted to cause a dedication of any component, step, feature, object, benefit, advantage, or equivalent to the public, regardless of whether it is or is not recited in the claims.

Claims (20)

1. A massively multiplayer online game (MMOG) monetization analysis computer system comprising:

an electronic data input interface configured to electronically receive data relevant to monetization of the MMOG, including player behavioral logs;

an electronic data processing system configured to electronically analyze the data received by the data input interface, including the player behavioral logs, in accordance with one or more algorithms and, based on the analysis, to predict player changes that are relevant to monetization of the MMOG and to generate a report relating to these predicted changes; and

an electronic data output interface configured to electronically deliver the report to an output device.

2. The MMOG monetization analysis computer system ofclaim 1 wherein the predicted player changes are indicative of predicted changes by individual players.

3. The MMOG monetization analysis computer system ofclaim 1 wherein the electronic data processing system is configured to extract longitudinal data from the player behavioral logs indicative of player behavior over a period of time and to consider this longitudinal data as part of the analysis.

4. The MMOG monetization analysis computer system ofclaim 3 wherein the longitudinal data is indicative of player behavior in multiple categories.

5. The MMOG monetization analysis computer system ofclaim 1 wherein the electronic data processing system is configured to extract cross-sectional cumulative data from the player behavioral logs indicative of how frequently players perform the same type of activity and to consider this cross-sectional data as part of the analysis.

6. The MMOG monetization analysis computer system ofclaim 1 wherein the electronic data processing system is configured to extract social networking data from the player behavioral logs indicative of player social networking while playing the MMOG and to consider this social networking data as part of the analysis.

7. The MMOG monetization analysis computer system ofclaim 1 wherein:

the data which the electronic data input interface is configure to electronically receive includes survey data indicative of the results of a survey of players and/or former players of the MMOG; and

the electronic data processing system is configured to consider this survey data as part of the analysis.

8. The MMOG monetization analysis computer system ofclaim 1 wherein:

the data which the electronic data input interface is configure to electronically receive includes game context data indicative of all or portions of the game context in which the data in the player behavioral logs took place; and

the electronic data processing system is configured to consider this game context data as part of the analysis.

9. The MMOG monetization analysis computer system ofclaim 1 wherein:

the data which the electronic data input interface is configure to electronically receive includes commercial outcome data indicative of changes in player subscriptions to the MMOG; and

the electronic data processing system is configured to consider this commercial outcome data as part of the analysis.

10. The MMOG monetization analysis computer system ofclaim 1 wherein the analysis identifies players whom are predicted to terminate their subscriptions to the MMOG.

11. The MMOG monetization analysis computer system ofclaim 1 wherein the analysis predicts an amount of time each of several players is likely to spend playing the MMOG.

12. The MMOG monetization analysis computer system ofclaim 1 wherein the analysis predicts a number of transactions each of a several players is likely to engage in while playing the MMOG.

13. The MMOG ofclaim 1 wherein the MMOG is a massively multiplayer role-playing online game (MMRPOG).

14. A process for maximizing monetization of a massively multiplayer online game (MMOG) comprising:

electronically receiving data relevant to monetization of the MMOG, including player behavioral logs;

electronically analyzing the received data, including the player behavioral logs, in accordance with one or more algorithms and, based on the analysis, predicting player changes that are relevant to monetization of the MMOG; and

modifying the MMOG to increase its monetization based on the predictions of the analysis.

15. The process ofclaim 14 wherein the predicted player changes are indicative of predicted changes by individual players.

16. The process ofclaim 14 wherein the analysis extracts from the player behavioral logs and considers longitudinal data indicative of player behavior over a period of time, cross-sectional cumulative data indicative of a how frequently players perform the same type of activity, and/or social networking data indicative of player social networking while playing the MMOG.

17. The process ofclaim 14 wherein the data which is analyzed includes an analysis of survey data indicative of the results of a survey of players and/or former players of the MMOG, game context data indicative of all or portions of the game context in which the data in the player behavioral logs took place, and/or commercial outcome data indicative of changes in player subscriptions to the MMOG.

18. The process ofclaim 14 wherein the analysis identifies players who are predicted to terminate their subscriptions to the MMOG.

19. The process ofclaim 14 wherein the analysis predicts how much time each of several players is likely to spend playing the MMOG over a time period.

20. The process ofclaim 14 wherein the analysis predicts a number of transactions each of several players is likely to engage in while playing the MMOG over a time period.

Images