The subject technology receives session data from a set of users associated with a retail website. The subject technology generates, using at least one machine learning model, a purchase intent prediction based at least in part on the session data. The subject technology determines a set of sessions that correspond to conversions on the retail website based on the session data. The subject technology generates a combination of data using first data from the purchase intent prediction with second data based on the set of sessions that correspond to conversions. The subject technology generates information related to a missed purchase segment based at least in part on the combination of data. The subject technology provides the information for display on a client device.

A system for awakening non-shopping consumers and an implementation method thereof employ artificial intelligence to grouping consumers, and then determine consumers who have not shopped for a long time, and provide products that meet consumers' needs by analyzing the results of the grouping, as the basis for consumers to shop. Moreover, the desire of consumers to buy goods can be promoted so as to awaken consumers who have not shopped for a long time.

There are provided systems and methods for linking user behaviors to tracked data consumption using digital tokens. A service provider, such as an online transaction processor, may provide additional services to users via a media content monitoring and/or tokenization system for purchasable items in media content. A user may view media content and see an item available for purchase. One or more IoT sensors, routers or devices, and the like may be used to identify the user viewed the item in the media content. This data may be tokenized as a shopping object digital token, which may be cached for a time period to detect if the user's behaviors indicate that the user purchases another related item based on viewing the item in the media content. If the user processes a transaction for the related item, rewards may be provided to participants involved in presenting and selling that item.

Systems and methods are presented for standardizing delivery of products in an online marketplace using one or more locker systems. In some embodiments, a system of lockers is presented. The locker system may be configured to store one or more products sold in an online marketplace. The locker system may also include a processor coupled to the one or more lockers and configured to generate access code information for a buyer to enable access to a locker storing the product. One or more sensors may be coupled to the one or more lockers and configured to examine the product for a level of product quality. A transmitter of the system may be configured to transmit the access code information to the buyer. The system can later accept the access code information inputted from the buyer and open the locker storing the product after receiving the access code information.

A system and method for preference determination, including obtaining permission for profile access from social media users where the users agree to participate in surveys. Profile data, preferences, and data from completed surveys is retrieved, and base odds are calculated for particular variables in profiles of respondents and of people in the general population, and attributes for which predictive targeted sets are desired are returned. The profile data, preferences, and survey data is analyzed using a combined index calculation method to reduce the profile data, preferences, and data from surveys to a single index value for one or more particular keywords. The variables are placed in rank order based on the single index value to determine a likelihood of a particular user to prefer a particular item, and a predictive targeted set is returned for a likelihood of users in a particular set of users to prefer a particular item.

Methods and apparatus for improving automatic selection and timing of messages by a machine or system of machines include an inductive computational process driven by log-level network data from mobile devices and other network-connected devices, optionally in addition to traditional application-level data from cookies or the like. The methods and apparatus may be used, for example, to improve or optimize effectiveness of automatically-generated electronic communications with consumers and potential consumers for achieving a specified target.

Cognitive assistants which use feedback to highlight relevant points of interest to a user so that recommendations can be provided to the user based upon learned knowledge of the users preferences, tastes and customs are provided. For this purpose a computer-implemented method includes capturing user data of a user from a plurality of sensors, determining a cognitive state of the user from the captured data, correlating the user data to the cognitive state of the user, and making recommendations to the user based on the correlation of the user data and the determined cognitive state of the user.

A method, computer system, and computer program product for cognitive elevator advertisements are provided. The embodiment may include identifying one or more passengers utilizing real-time sensor data. The embodiment may also include determining a preference value of each identified passenger for a plurality of product categories based on a plurality of data related to past purchase histories or purchasing patterns received from a plurality of databases simultaneously or almost simultaneously. The embodiment may further include computing corrected passenger preference values for the plurality of product categories based on unprejudiced preference values of the passengers multiplied by the preference values assigned to each product category. The embodiment may also include determining one or more targeted advertisements for one or more targeted passengers based on each computed passenger preference values. The embodiment may further include displaying one or more advertisements on one or more display screens within an elevator based on the one or more targeted advertisements.

A campaign profile specifies products and/or content items associated with a campaign. A target group selection engine applies an affinity attribute model to user information of a user. The affinity attribute model is used to determine the user's affinity towards (a) product attributes of the products associated with the campaign and/or (b) content attributes of the content items associated with the campaign. The affinity attribute model may be generated using machine learning. A user interface accepts target user tuning parameters that specify weights to be applied to the affinity attributes determined by the affinity attribute model. Based at least on applying the weights to the affinity attributes, an inclusion score and/or exclusion score for the user is determined. The user is included in a target group, for engaging with the campaign, based on the inclusion score and/or exclusion score.

Techniques are disclosed for delivering electronically generated offers to particular users, and more particularly, for obtaining and receiving data of particular types from specified sources to provide output that is generated from a decisioned library. The techniques include retrieving a product score that comprises a probability that a first user will obtain a first product, obtaining a behavioral value, and generating a score of a behavior value. The score of the first product behavioral value is then mathematically combined with a similarly derived second score of a product behavioral value to determine whether to generate and deliver an offer to the first user.