Abstract: Embodiments are directed to representing documents using document keys. Documents that include one or more clauses may be provided. Each clause type for the one or more clauses in documents may be determined based on one or more classification models. One or more clause identifiers may be associated with the one or more clauses based on one or more clause types of each clause. A document key may be generated for each document based on an ordered collection of the one or more clauses included in each document such that each clause identifier may be positioned in the document key based on an order of its location in a corresponding clause of a document. The documents may be analyzed based on evaluations of one or more document keys corresponding to the documents. One or more reports may be generated based on one or more results of the analysis.

Abstract: Embodiments are directed to representing documents using document keys. Documents that include one or more clauses may be provided. Each clause type for the one or more clauses in documents may be determined based on one or more classification models. One or more clause identifiers may be associated with the one or more clauses based on one or more clause types of each clause. A document key may be generated for each document based on an ordered collection of the one or more clauses included in each document such that each clause identifier may be positioned in the document key based on an order of its location in a corresponding clause of a document. The documents may be analyzed based on comparisons of one or more document keys corresponding to the documents. One or more reports may be generated based on one or more results of the analysis.

Abstract: Embodiments are directed to managing documents over a network. A machine learning (ML) engine analyzes a plurality of documents associated with actions that were performed previously. The ML engine determines critical events associated with the performance of the actions based on the plurality documents. The ML engine generates ML models based on the critical events to compute risk values that may be associated with the critical events. In response to a request to compute risk values associated with pending actions, the ML engine determines documents that are associated with the pending actions based on the request. The ML engine determines the critical events associated with pending actions based on the documents. The ML engine employs the ML models to generate the risk values based on the documents and the critical events. The ML engine provides the risk values in response to the request.

Abstract: Embodiments are directed to managing documents over a network. A machine learning (ML) engine analyzes a plurality of documents associated with actions that were performed previously. The ML engine determines critical events associated with the performance of the actions based on the plurality documents. The ML engine generates ML models based on the critical events to compute risk values that may be associated with the critical events. In response to a request to compute risk values associated with pending actions, the ML engine determines documents that are associated with the pending actions based on the request. The ML engine determines the critical events associated with pending actions based on the documents. The ML engine employs the ML models to generate the risk values based on the documents and the critical events. The ML engine provides the risk values in response to the request.

Abstract: Embodiments are directed to managing documents over a network. A machine learning (ML) engine analyzes a plurality of documents associated with actions that were performed previously. The ML engine determines critical events associated with the performance of the actions based on the plurality documents. The ML engine generates ML models based on the critical events to compute risk values that may be associated with the critical events. In response to a request to compute risk values associated with pending actions, the ML engine determines documents that are associated with the pending actions based on the request. The ML engine determines the critical events associated with pending actions based on the documents. The ML engine employs the ML models to generate the risk values based on the documents and the critical events. The ML engine provides the risk values in response to the request.

Abstract: Embodiments are directed to managing documents over a network. A machine learning (ML) engine analyzes a plurality of documents associated with actions that were performed previously. The ML engine determines critical events associated with the performance of the actions based on the plurality documents. The ML engine generates ML models based on the critical events to compute risk values that may be associated with the critical events. In response to a request to compute risk values associated with pending actions, the ML engine determines documents that are associated with the pending actions based on the request. The ML engine determines the critical events associated with pending actions based on the documents. The ML engine employs the ML models to generate the risk values based on the documents and the critical events. The ML engine provides the risk values in response to the request.

Abstract: A system, computer-readable storage medium storing at least one program, and a computer-implemented method for detecting fraud in a social gaming environment is disclosed herein. For example, game events generated responsive to a player playing a game executing on a client device are received. The game events may then be used to build a player profile for the player. The player profile may characterize the game actions performed by the player. The player profile is then compared with a golden profile. The golden profile may specify an expected gaming behavior. Based on the comparison between the player profile and the expected gaming behavior specified by the golden profile, a player account associated with the player may be marked as suspicious.

Abstract: A system, computer-readable storage medium storing at least one program, and a computer-implemented method for detecting fraud in a social gaming environment is disclosed herein. For example, game events generated responsive to a player playing a game executing on a client device are received. The game events may then be used to build a player profile for the player. The player profile may characterize the game actions performed by the player. The player profile is then compared with a golden profile. The golden profile may specify an expected gaming behavior. Based on the comparison between the player profile and the expected gaming behavior specified by the golden profile, a player account associated with the player may be marked as suspicious.

Abstract: A system, computer-readable storage medium storing at least one program, and a computer-implemented method for detecting fraud in a social gaming environment is disclosed herein. For example, game events generated responsive to a player playing a game executing on a client device are received. The game events may then be used to build a player profile for the player. The player profile may characterize the game actions performed by the player. The player profile is then compared with a golden profile. The golden profile may specify an expected gaming behavior. Based on the comparison between the player profile and the expected gaming behavior specified by the golden profile, a player account associated with the player may be marked as suspicious.