Abstract: A method for testing a new feature of an online gaming application is provided. The method initiates with assigning each of a plurality of users to one of a test group and a control group. Each of the test group users is provided a gaming application including a new game feature enabled, and each of the control group users is provided the gaming application without the new game feature enabled. Gaming activity and social network activity of the test group users is evaluated to generate an evaluation score for the test group users. Gaming activity and social network activity of the control group users is evaluated to generate an evaluation score for the control group users.

Abstract: A method for testing a new feature of an online gaming application is provided. According to the method, a gaming application request is received from a user, and it is determined whether to add the user to a live test for a new game feature. If the user is added to the live test, then the user is assigned to a test group or a control group. If the user is assigned to the test group, then a gaming application is provided including the new game feature enabled. If the user is assigned to the control group, then the gaming application is provided without the new game feature enabled. User social graph data identifying co-users of the user is obtained, and gaming activity and social network activity of the user is evaluated.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR AN ONLINE BEHAVIOR MONITOR (“OBM”) transform user social-gaming behavioral pattern data via various OBM components into online social-gaming experience customizations. In one embodiment, the OBM may generate individual social-gaming activity timelines for a group of users within a geographical region using user online gaming pattern and social activity data. The OBM may calculate individual time-varying activity level graphs for the users, as well as an aggregate activity level graph. The OBM may identify an activity trough in the aggregate activity level graph, and an event in the geographical region corresponding to the activity level trough. Based on keywords corresponding to the event, the OBM may obtain product results from a product database.

Abstract: Methods for detecting fraud using virtual currency transaction include receiving information regarding a virtual currency transaction from a user. The information is analyzed to determine whether the transaction involves a user that is being tracked, wherein the user being tracked is associated with an elevated level of risk of fraud. When a user associated with the transaction is being tracked, the virtual currency transaction is monitored using tracked virtual currency. The virtual currency transaction is identified as potentially fraudulent based on the monitoring.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR AN ONLINE BEHAVIOR MONITOR (“OBM”) transform user social-gaming behavioral pattern data via various OBM components into online social-gaming experience customizations. In one embodiment, the OBM may provide, in response to a gaming app request from a user, a gaming app including a test game feature for the user. The OBM may obtain user social graph data identifying co-users of the user. The OBM may also obtain: online gaming pattern data for the users and the co-users, including gaming action identifiers and their associated gaming action timestamps; user online social activity data, for the users and the co-users, including social networking action identifiers and their associated social networking action timestamps; and game feature adoption evaluation instructions.

Abstract: The APPARATUSES, METHODS AND SYSTEMS FOR A TRACKABLE VIRTUAL CURRENCIES PLATFORM (“TVC”) transform user transaction request input via various TVC components into transaction result output. In one embodiment, information regarding a virtual currency transaction including a user identifier of a user associated with the virtual currency transaction may be received. A potential fraud event threshold score for the user may be calculated by analyzing past fraud data associated with the user, and a virtual currency transaction fraud score may be calculated by analyzing the user's social graph and the user's prior game play patterns. If the virtual currency transaction fraud score exceeds the potential fraud event threshold score for the user, the virtual currency transaction may be identified as potentially fraudulent.