# US 2021/0241347 A1 · Single-select predictive platform model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241347 A1 - Document ID: US20210241347A1 - Status: Published application - Kind: A1 - Application number: 16/779,254 - Filed: 2020-01-31 - Published: 2021-08-05 - Earliest claimed: 2020-01-31 - Assignees: Walmart Apollo, LLC - Applicants: Walmart Apollo, LLC - Inventors: Rahul Sridhar; Sinduja Subramaniam; Tejal Kumar Patted; Evren Korpeoglu; Kannan Achan; Rahul Ramkumar; Mark Richards Ibbotson; Thomas Russel Ward; Ryan Wayne Travis; Vidyanand Krishnan; Lucinda Frink Newcomb - Web page: https://patentgrep.com/patent/US20210241347A1 ## CPC - G06Q 30/0631: {Recommending goods or services} - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/09: Supervised learning - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06Q 30/02: Marketing; Price estimation or determination; Fundraising - G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)} - G06Q 30/0641: {utilising user interfaces specially adapted for shopping} - G06N 3/045: Combinations of networks - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 20/20: Ensemble learning - G06Q 30/0601: Electronic shopping [e-shopping] - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## 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 receiving the single-click option, adding the all selected items of the set of items to the cart. Other embodiments are disclosed. ## Claims ### Claim 1 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, 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 receiving the single-click option, adding the all selected items of the set of items to the cart. ### Claim 2 (depends on 1) The system of claim 1, wherein: the previous transactions comprise online transactions and in-store transactions made by the user and the other users within a first period of time occurring before the present time; the previous transactions are stored in a database along with order times of the online transactions and the in-store transactions; and determining the set of items further comprises: determining the set of items as a subset of multiple items within the previous transactions based on the probability that the user will re-order the each item of the set of items at the present time exceeding the predetermined threshold. ### Claim 3 (depends on 1) The system of claim 1, wherein determining the set of items further comprises: determining the set of items using a logistic regression model to predict the probability based on the previous transactions. ### Claim 4 (depends on 3) The system of claim 3, wherein: the logistic regression model is trained on training data received, as refreshed during a second period of time; the training data comprises features generated by order history of the user and the other users within a second period of time; the logistic regression model learns through an iterative process using the training data, as refreshed; and a performance of the logistic regression model is evaluated against a set of periodic frequencies of the online transactions and the in-store transactions for the each item of the set of items to predict a confidence level of the probability. ### Claim 5 (depends on 1) The system of claim 1, wherein determining the set of items further comprises: determining the set of items using a decision tree model to predict the probability by calculating a value of at least a target variable using random forests and gradient boosted trees. ### Claim 6 (depends on 1) The system of claim 1, wherein determining the set of items further comprises: determining the set of items using a recurrent neural network model to predict the probability by utilizing model temporal sequences of data comprising (i) previous transactions of the user and the other users and (ii) cart compositions of the user and other users. ### Claim 7 (depends on 1) The system of claim 1, wherein determining the set of items further comprises: determining the set of items using a multi-level learning model to predict the probability by analyzing: (i) a first model of user behavior to predict a category the user is likely to visit on the page; and (ii) a second model to predict a likelihood that the user will re-order an item from the category. ### Claim 8 (depends on 1) The system of claim 1, wherein sending the instructions to display the set of items to the user on the user interface further comprises: sending instructions to display a scrolling module on the user interface, wherein: the scrolling module is configured to display the set of items across multiple scrolling pages; each of the multiple scrolling pages comprise icons for a respective subset of the set of items; each item in the respective subset of the set of items is automatically selected as the user scrolls to display a respective page of the multiple scrolling pages; and the all selected items added to the cart comprise automatically selected items of the respective subsets of the items that have been displayed by the user scrolling through one or more of the multiple scrolling pages. ### Claim 9 (depends on 1) The system of claim 1, wherein sending instructions to display the set of items to the user on the user interface further comprises: sending instructions to display one or more deselection options to remove one or more items of the set of items from the all selected items, wherein a model used to determine the probability is updated for future determinations based on the user deselecting the one or more items using the one or more of the deselection options. ### Claim 10 (depends on 1) The system of claim 1, wherein: the user interface displays quantity selection options to change a quantity of one or more items in the set of items; and a model used to determine the probability is updated for future determinations based on the user changing the quantity using one or more of the quantity selection options. ### Claim 11 A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising: 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, 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 receiving the single-click option, adding the all selected items of the set of items to the cart. ### Claim 12 (depends on 11) The method of claim 11, wherein: the previous transactions comprise online transactions and in-store transactions made by the user and the other users within a first period of time occurring before the present time; the previous transactions are stored in a database along with times of purchase of the online transactions and the in-store transactions; determining the set of items further comprises: determining the set of items as a subset of multiple items within the previous transactions based on the probability that the user will re-order the each item of the set of items at the present time exceeding the predetermined threshold. ### Claim 13 (depends on 11) The method of claim 11, wherein determining the set of items further comprises: determining the set of items using a logistic regression model to predict the probability based on the previous transactions. ### Claim 14 (depends on 13) The method of claim 13, wherein: the logistic regression model is trained on training data received, as refreshed during a second period of time; the training data comprises features generated by previous transactions of the user and the other users within a second period of time; the logistic regression model learns through an iterative process using the training data, as refreshed; and a performance of the logistic regression model is evaluated against a set of periodic frequencies of the online transactions and the in-store transactions for the each item of the set of items to predict a confidence level of the probability. ### Claim 15 (depends on 11) The method of claim 11, wherein determining the set of items further comprises: determining the set of items using a decision tree model to predict the probability by calculating a value of at least a target variable using random forests and gradient boosted trees. ### Claim 16 (depends on 11) The method of claim 11, wherein determining the set of items further comprises: determining the set of items using a recurrent neural network model to predict the probability by utilizing model temporal sequences of data comprising (i) previous transactions of the user and the other users and (ii) cart compositions of the user and other users. ### Claim 17 (depends on 11) The method of claim 11, wherein determining the set of items further comprises: determining the set of items using a multi-level learning model to predict the probability by analyzing: (i) a first model of user behavior to predict a category the user is likely to visit on the page; and (ii) a second model to predict a likelihood that the user will re-order an item from the category. ### Claim 18 (depends on 11) The method of claim 11, wherein sending the instructions to display the set of items to the user on the user interface further comprises: sending instructions to display a scrolling module on the user interface, wherein: the scrolling module is configured to display the set of items across multiple scrolling pages; each of the multiple scrolling pages comprise icons for a respective subset of the set of items; each item in the respective subset of the set of items is automatically selected as the user scrolls to display a respective page of the multiple scrolling pages; and the all selected items added to the cart comprise automatically selected items of the respective subsets of the items that have been displayed by the user scrolling through one or more of the multiple scrolling pages. ### Claim 19 (depends on 11) The method of claim 11, wherein sending instructions to display the set of items to the user on the user interface further comprises: selecting one or more deselection options to remove one or more items of the set of items from the all selected items, wherein a model used to determine the probability is updated for future determinations based on the user selecting the one or more of the deselection options. ### Claim 20 (depends on 11) The method of claim 11, wherein: the user interface displays quantity selection options to change a quantity of one or more items in the set of items; and a model used to determine the probability is updated for future determinations based on the user changing the quantity using one or more of the quantity selection options.