Abstract: A set of data for training a machine learning system can be modified to improve its performance. An item of information can be transmitted. A message can be transmitted that includes an explanation of a determination, by the machine learning system, to transmit the item of information from among a plurality of items of information. A first set of data can have been used to train the machine learning system. A signal can be received that includes an indication of a usefulness of the message, to a user of a user device, in making a decision to perform an action based on a knowledge associated with the item of information. The first set of data can be modified, in response to a receipt of the signal, to produce a second set of data. The machine learning system can be caused to be trained using the second set of data.

Abstract: The system and methods of the disclosed subject matter provide an experimentation framework to allow a user to perform machine learning experiments on tenant data within a multi-tenant database system. The system may provide an experimental interface to allow modification of machine learning algorithms, machine learning parameters, and tenant data fields. The user may be prohibited from viewing any of the tenant data or may be permitted to view only a portion of the tenant data. Upon generating an experimental model using the experimental interface, the user may view results comparing the performance of the experimental model with a current production model.

Abstract: A set of data for training a machine learning system can be modified to improve its performance. An item of information can be transmitted. A message can be transmitted that includes an explanation of a determination, by the machine learning system, to transmit the item of information from among a plurality of items of information. A first set of data can have been used to train the machine learning system. A signal can be received that includes an indication of a usefulness of the message, to a user of a user device, in making a decision to perform an action based on a knowledge associated with the item of information. The first set of data can be modified, in response to a receipt of the signal, to produce a second set of data. The machine learning system can be caused to be trained using the second set of data.

Abstract: A system may automatically generate a predictive machine learning model by automatically performing various processes based on an analysis of the data as well as metadata associated with the data. The system may accept a selection of data and a prediction field from the data. The system may automatically generate a set of features based on the data and may automatically remove certain features that cause inaccuracies in the model. The system may balance the data based on a representation rate of certain outcomes. The system may train and select a model based on several candidate models. The system may then perform the predictions based on the selected model and send an indication of the predictions to a user.

Abstract: A method for generating a model for recommendations from an item data set for a target data set includes embedding a set of targets from the target data set in a shared coordinate space using a first embedding function, embedding a first set of items from the item data set in the shared coordinate space using a second embedding function, selecting at least one target from the set of targets, and identifying a second set of items from the first set of items that are proximate to the at least one target as candidates from the recommendations.

Abstract: A set of data for training a machine learning system can be modified to improve its performance. An item of information can be transmitted. A message can be transmitted that includes an explanation of a determination, by the machine learning system, to transmit the item of information from among a plurality of items of information. A first set of data can have been used to train the machine learning system. A signal can be received that includes an indication of a usefulness of the message, to a user of a user device, in making a decision to perform an action based on a knowledge associated with the item of information. The first set of data can be modified, in response to a receipt of the signal, to produce a second set of data. The machine learning system can be caused to be trained using the second set of data.

Abstract: The system and methods of the disclosed subject matter provide an experimentation framework to allow a user to perform machine learning experiments on tenant data within a multi-tenant database system. The system may provide an experimental interface to allow modification of machine learning algorithms, machine learning parameters, and tenant data fields. The user may be prohibited from viewing any of the tenant data or may be permitted to view only a portion of the tenant data. Upon generating an experimental model using the experimental interface, the user may view results comparing the performance of the experimental model with a current production model.

Abstract: Techniques for inferring the identity (e.g., member profile attributes) of members of an online social network service are described. According to various embodiments, a member profile attribute missing from a member profile page associated with a particular member of an online social network service is identified. Member profile data and behavioral log data associated with a plurality of members of the online social network service is then accessed. Thereafter, a prediction modeling process is performed, based on a prediction model and feature data including the member profile data and the behavioral log data, to generate a confidence score associated with the particular member and the missing member profile attribute, the confidence score indicating a likelihood that the missing member profile attribute corresponds to a candidate value.

Abstract: A system may automatically generate a predictive machine learning model by automatically performing various processes based on an analysis of the data as well as metadata associated with the data. The system may accept a selection of data and a prediction field from the data. The system may automatically generate a set of features based on the data and may automatically remove certain features that cause inaccuracies in the model. The system may balance the data based on a representation rate of certain outcomes. The system may train and select a model based on several candidate models. The system may then perform the predictions based on the selected model and send an indication of the predictions to a user.

Abstract: A title standardization system is may be configured to detect an edit operation associated with the job title field of a member profile stored by an on-line social network system and, in response, perform operations to derive a canonical title that represents a raw title string found in the job title field. The derived canonical title may be then associated with the member profile, in which the originally-obtained subject title string was found. This association may be stored in a database for future use, e.g., for targeting job recommendations, recruiting, making professional contacts, as well as for other purposes.

Abstract: In order to determine seniority associated with a title string associated with a member profile in an on-line social network system, a standardization system may be configured to operate as follows. A standardization system may determine a canonical title that corresponds to the title string, determine any seniority modifiers that may be present in the title string, and calculate a seniority value for the title sting as the sum of the seniority value assigned to the determined canonical title and the respective seniority values of the determined seniority modifiers. A seniority modifier is a phrase comprising one or more words that have been identified as being indicative of seniority if included in a title string.

Abstract: A title standardization system may be configured to automatically identify modifier terms in title strings and store these terms in a dictionary for future use. Modifier terms are those phrases in a title string that have been identified as indicative of a certain aspect related to the job of the associated member. In order to identify modifier terms, a title standardization system examines transitions between jobs that the members of the on-line social network system have reported via their respective profiles. If a transition pair comprising a first title string and a second title string was determined to be conforming to a stable pattern, a phrase that is included in the first title string and is lacking from the second title string is identified as a modifier phrase and stored in a dictionary for future use.

Abstract: A seniority standardization system may be configured to derive seniority values in the context of an on-line social network system. In order to determine a seniority rank of a given professional title, a seniority standardization system may leverage transition data, which is information that may be gleaned from a member profile with respect to the member's transition from one professional position to another. A seniority standardization system may also use time-based seniority signal. A time-based seniority value, which may be assigned to a particular professional title, is the amount of time that it typically takes to achieve a professional position represented by that particular professional title.

Abstract: A title standardization system is may be configured to detect an edit operation associated with the job title field of a member profile stored by an on-line social network system and, in response, perform operations to derive a canonical title that represents a raw title string found in the job title field. The derived canonical title may be then associated with the member profile, in which the originally-obtained subject title string was found. This association may be stored in a database for future use, e.g., for targeting job recommendations, recruiting, making professional contacts, as well as for other purposes.

Abstract: Techniques for inferring the identity (e.g., member profile attributes) of members of an online social network service are described. According to various embodiments, a member profile attribute missing from a member profile page associated with a particular member of an online social network service is identified. Member profile data and behavioral log data associated with a plurality of members of the online social network service is then accessed. Thereafter, a prediction modeling process is performed, based on a prediction model and feature data including the member profile data and the behavioral log data, to generate a confidence score associated with the particular member and the missing member profile attribute, the confidence score indicating a likelihood that the missing member profile attribute corresponds to a candidate value.

Abstract: Method and system to infer seniority level of a social network member is provided. The system includes a transition data extractor, a token extractor, a transition data analyzer, and a storing module. The transition data extractor extracts transition data from member profiles maintained in an online social network system. The token extractor extracts a plurality of tokens from title strings in the transition data. The transition data analyzer analyzes the transition data to generate a weight for each token in the plurality of tokens. A weight for a token in the plurality of tokens indicates a contribution of the token to a seniority rank of a title string that includes the token. The storing module stores the plurality of tokens and their associated weights in a database.

Abstract: Method and system to create a job function ontology may be utilized to derive, from member profiles maintained in an on-line social networking system, job function entities associated with respective sets of professional attributes. An entry in the job function ontology—a job function entity—may include identification of the associated job function, as well as a set of professional attributes that characterize professional skills of a member of the on-line social network system. A label assigned to a job function entity may be viewed as a standardized job title.

Abstract: A system and method for automatically classifying ads into a taxonomy of categories, the method including: extracting text features from ad images using OCR (optical character recognition) techniques; identifying objects of interest from ad images using object detection and recognition techniques in computer vision; extracting text features from the web-page of the advertiser to which the user is re-directed when clicking the ad; training statistical models using the extracted features mentioned above as well as advertiser attributes from a historical dataset of ads labeled by human editors; and determining the relevant categories of unlabeled ads using the trained models.

Abstract: A system and method for automatically classifying ads into a taxonomy of categories, the method including: extracting text features from ad images using OCR (optical character recognition) techniques; identifying objects of interest from ad images using object detection and recognition techniques in computer vision; extracting text features from the web-page of the advertiser to which the user is re-directed when clicking the ad; training statistical models using the extracted features mentioned above as well as advertiser attributes from a historical dataset of ads labeled by human editors; and determining the relevant categories of unlabeled ads using the trained models.