Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform acts of: generating a feature vector for a user based, at least in part, on historical data pertaining to the user's previous transactions; generating, using a quantity prediction model of a machine learning architecture, a respective item quantity prediction for each of one or more items included in a predicted basket based, at least in part, on the feature vector for the user; and populating a respective quantity selection option for each of the one or more items included in the predicted basket based on the respective item quantity prediction generated for each of the one or more items. Other embodiments are disclosed herein.

Abstract: A privacy system includes a computing device configured to obtain user transactional data characterizing at least one transaction of a user on an ecommerce marketplace and to determine a privacy vulnerability score of the user by comparing the transactional data to a user vulnerability distribution. The computing device is also configured to send the privacy vulnerability score to a personalization engine.

Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform functions comprising: generating one or more feature vectors for a user, the one or more feature vectors at least comprising transaction-based features and slot-based features; generating, using a machine learning architecture, a repurchase prediction for the user based, at least in part, on the one or more feature vectors; generating, using the machine learning architecture, a time slot prediction for the user based, at least in part, on the one or more feature vectors, the time slot prediction predicting a time slot desired by the user for an upcoming transaction; and executing a reservation function that facilitates reserving of the time slot for the user. Other embodiments are disclosed herein.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform functions comprising: receiving one or more vectors representing one or more types of features for a pair of items; generating, using a similarity item model of a machine learning architecture, a prediction for a similar item, wherein the similarity item model combines a pair of separately trained machine learning models; combining a first output of the gradient boosted model and a second output of the neural network model to generate a similarity score for the pair of items; and transmitting the similar item to a first position on a carousel display of a website that concurrently displays the anchor item on the website. Other embodiments are disclosed.

Abstract: A recommender system can include a defender computing device that is configured to obtain customer interaction data characterizing customer interactions with an ecommerce marketplace. The defender computing device can also be configured to determine an item recommendation based on the customer interaction data using a trained differentially private recommendation model and send the item recommendation to the customer. The trained differentially private recommendation model is more likely to determine the same item recommendation after poisoned data is injected into the customer interaction data than a recommendation model that is not privately trained.

Abstract: This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Abstract: This application relates to apparatus and methods for automatically detecting attacks to advertisement systems. In some examples, a computing device trains a machine learning process based on a training dataset. The training dataset may be an identified portion of a website session dataset that includes a lower percentage of malicious data caused by attacks than other portions, or may include no malicious data. Once trained, the computing device generates features from a website session dataset for a customer, and applies the trained machine learning process to the generated features to detect malicious data within the website session dataset for the customer. Further, the computing device may filter the website session data to remove the detected malicious data, and may store the filtered website session data within a data repository. The computing device may provide the filtered website session data to a recommendation system to generate item recommendations for the customer.

Abstract: An approach is disclosed for recommending complementary items based on customer shopping routines. The approach receives anchor item data. The approach identifies a routine that corresponds to the anchor item data. The routine is based on an item purchasing behavior of a customer. The approach determines categorical data within the identified routine by applying a ranking algorithm to the categorical data of the categories and the anchor item data. The categorical data is relevant to the anchor item data. The approach generates relevant item data from the categorical data by applying an item recommendation model to item data that corresponds to the categorical data.

Abstract: A method can include modeling a webpage as a random field. The random field can include an undirected graph including two or more nodes and one or more edges. A goodness function can be associated with one or more webpage elements. Each edge of the one or more edges can include a compatibility function based at least in part on the one or more goodness functions of two different nodes of the two or more nodes. The method also can include determining a probability of the webpage having exceeded a predetermined threshold based at least in part on one or more of the compatibility functions of the one or more edges. Other embodiments are disclosed.

Abstract: This application relates to apparatus and methods for automatically identifying substitute items. A computing device can generate matrix data that identifies connection values between a plurality of items. The matrix data may be generated based on the application of one or more machine learning algorithms to historical data identifying accepted or denied item substitutions. The computing device may then receive item data identifying at least one second item and at least one attribute of that second item. The computing device may generate a graph based on the matrix data and the item data to determine connection values between the second item and the plurality of first items. The computing device may then determine a substitute item (e.g., a replacement item) for the second item based on the connection values between the second item and the plurality of first items.

Abstract: A method including tracking impression response data in response to online impressions of content elements displayed to users of a website. The impression response data can include (i) first responses by the users in one or more physical stores in response to the online impressions, and (ii) second responses by the users in the website in response to the online impressions. The method also can include receiving a request from a user of the users to display a webpage of the website. The method additionally can include generating the webpage to include a content element selected from among the content elements based on a classification of the user and the impression response data for the content elements. Other embodiments of related systems and methods are described.

Abstract: Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: utilizing historical transaction information to derive metric information associated with prior transactions; generating a listing of user-item pairs, each of the user-item pairs identifying a user and an item; executing a machine learning model that is configured to generate a transmission list for sending push notifications; generating a transmission list by selecting user-item pairs based on the conversion probability values and the confidence indicators that are assigned to the user-item pairs; customizing content for the push notifications to include information for items identified by the user-item pairs included in the transmission list; and transmitting the push notifications to the users identified by the user-item pairs included in the transmission list.

Abstract: A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform: determining a set of items to recommend to a user based on a probability exceeding a predetermined threshold that the user will re-order each item of the set of items at a present time, wherein the probability is determined based at least in part on previous transactions of the user and other users within a first period of time, and wherein the set of items includes at least a predetermined number of items; sending instructions to display the set of items to the user on a user interface, wherein at least a portion of the set of items is shown as selected on the user interface, and the user interface further comprises a single-click option to add to a cart all selected items of the set of items; receiving a selection of the single-click option to add to the cart the all selected items of the set of items; and after receivin

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, perform certain acts. The acts can include obtaining reorder likelihood scores for items that a user has ordered historically. The acts also can include grouping the items into groups using a taxonomy. The acts additionally can include adjusting the groups based on a respective number of items in each of the groups and a respective group-specific threshold for each of the groups. The acts further can include ranking the items within the groups based on the reorder likelihood scores. Other embodiments are described.

Abstract: An approach is disclosed for recommending trending complementary items or trending similar items. The approach receives anchor item data corresponding to an anchor item. The approach determines a subcategory data corresponding to a category of the anchor item. The approach identifies an attribute label of the anchor item subcategory data, in which the attribute label indicates whether the anchor item is eligible for up-selling. The approach identifies, in response to the attribute label indicating that the anchor item is not eligible for up-selling, complementary subcategory data corresponding to the anchor item subcategory data, based on historical transaction data and at least one of co-view data and add-to-cart data. The approach generates recommended cross-selling item data from the complementary subcategory data, the recommended cross-selling item data being generated by applying a trending model to historical transaction data of items having complementary subcategory data.

Abstract: An approach is disclosed for recommending complementary items based on customer shopping routines. The approach receives anchor item data. The approach identifies a routine that corresponds to the anchor item data. The routine is based on an item purchasing behavior of a customer. The approach determines categorical data within the identified routine by applying a ranking algorithm to the categorical data of the categories and the anchor item data. The categorical data is relevant to the anchor item data. The approach generates relevant item data from the categorical data by applying an item recommendation model to item data that corresponds to the categorical data.

Abstract: This application relates to apparatus and methods for automatically identifying substitute items. A computing device can generate matrix data that identifies connection values between a plurality of items. The matrix data may be generated based on the application of one or more machine learning algorithms to historical data identifying accepted or denied item substitutions. The computing device may then receive item data identifying at least one second item and at least one attribute of that second item. The computing device may generate a graph based on the matrix data and the item data to determine connection values between the second item and the plurality of first items. The computing device may then determine a substitute item (e.g., a replacement item) for the second item based on the connection values between the second item and the plurality of first items.

Abstract: This application relates to apparatus and methods for providing a unified serving platform that allows for the reusability of machine learning models across a plurality of websites to determine personalized content. For example, a computing device trains a machine learning model with session data identifying browsing events and transaction data identifying purchasing events for a plurality of users. The computing device receives and stores session data and transaction data associated with a first website for the customer. The computing device may then receive a request for content to display to the customer on a second website. The computing device generates label data based on the session data and transaction data associated with the first website, and executes the trained machine learning model with the label data. Based on execution of the trained machine learning model, the computing device generates content to display on the second website, and transmits the content.

Abstract: Systems and methods including one or more processors and one or more non-transitory computer readable storage devices storing computing instructions configured to run on the one or more processing modules and perform: gathering first data comprising first interactions of a user with a first graphical user interface; storing the first data comprising the first interactions of the user with the first graphical user interface as at least one first vector by adding to the at least one first vector for each level of a hierarchical categorization of the first user interface; gathering second data comprising second interactions of the user with a second graphical user interface; storing the second data comprising the second interactions of the user with the second graphical user interface as at least one second vector; determining an intent of the user using the at least one first vector, the at least one second vector, and a predictive algorithm; and transmitting instructions to display a third graphical user inter

Abstract: A method including tracking usage data for users using a first channel and a second channel. The method also can include performing a classification of first users of the users into a first group and second users of the users into a second group. The classification can be based on the usage data. The method additionally can include, for each impression of a content element of content elements being displayed on a website to a user of the users, tracking impression response data including (a) whether the user is grouped into the first group or the second group, and (b) response data including: (i) a first response by the user to the content element in the first channel, and (ii) a second response by the user to the content element in the second channel. The method further can include receiving a request from a first user of the users to display a webpage of the website. The method additionally can include generating the webpage to include a selected content element from among the content elements.