Abstract: Approaches are provided that determine and fine-tune product assortments carried by retail stores. In aspects, the number of stores that carry the item, the sales performance of the item, the loyalty of customers to the item, whether substitutes for the item can be found, and other factors are used to determine an actions such as increasing or decreasing the shelf space for an item.

Abstract: A method for computer modeling a retail environment includes: calculating a space elasticity for an item of an item category in a retail store, using a constrained linear regression model; calculating a cross-space elasticity for the item of the item category in the retail store, using a multiple regression model; generating a number for horizontal facings for the item of the item category in the retail store, using a non-linear multiple-constraint mixed integer optimization model, based on the space elasticity of the item and the cross-space elasticity of the item; and generating an electronic planogram of the item category for the retail store, based on the number of the horizontal facings of the item.

Abstract: This application relates to systems and methods for automatically detecting and correcting image quality based on a set of quality standards. In some examples, a plurality of quality parameters of an image are determined based on receiving an image. It is then determined that at least one of the plurality of quality parameters is below a predetermined threshold. The predetermined threshold may be based on a required quality standard for images. In response to determining that the at least one of the plurality of quality parameters is below the predetermined threshold, feature of the image is adjusted such that the at least one of the plurality of quality parameters is at or above the predetermined threshold.

Abstract: Systems and methods for generating training data, and training machine learning models with the generated training data, are disclosed. In some examples, a computing device obtains, from a data repository, training data, wherein the training data comprises labelled samples and unlabeled samples. The computing device generates clusters of the training data based on one or more corresponding attributes of the training data. Further, the computing device determines a distance metric between positively labelled samples and unlabeled samples within each cluster, and generates, for each of the clusters, a plurality of sub-clusters based on the determined distance metrics. The computing device also determines, from each of the plurality of sub-clusters, one or more of the unlabeled samples based on a corresponding reward value and a corresponding sampling rate value. The computing device may train a machine learning model with the determined unlabeled samples from each of the plurality of sub-clusters.

Abstract: Initial sales cluster is divided by the control circuit into a plurality of velocity buckets. Subsequently, each velocity bucket is divided into a plurality of micro-clusters. The micro-clusters are defined according to demographic information or store characteristic information. A importance score and a performance score for each of the micro-clusters is determined. An optimal sales cluster and a corresponding optimal planogram for each retail store in each micro-cluster are determined based upon the importance score and the performance score.

Abstract: A systems 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: receiving a plurality of images from one or more devices, the images corresponding to a store shelf of a store; combining the plurality of images to generate a shelf image corresponding to the store shelf; encoding the shelf image into a first processing format; processing the shelf image in the first processing format with a neural network using pre-trained weights; determining positions in the shelf image that correspond to an out-of-stock detection based on outputs from the neural network; and generating a report for the out-of-stock detection, the report including an indication of coordinates of the out-of-stock detection and an item of the store that corresponds to the coordinates. Other embodiments are described.

Abstract: This application relates to automated processes for determining item placement compliance within retail locations. For example, a computing device may obtain an image of a fixture within a store. The image may be captured by a camera with a field of view directed at the fixture. The computing device may apply a segmentation process to the image to determine a portion of the image. Further, the computing device may determine a correlation between the portion of the image and each of a plurality of item image templates. Each item image template may include an image of an item the retail location sells in the retail location. The computing device may determine, based on the correlations, one of the plurality of item image templates and its corresponding item. The computing device may then determine whether the item should be located at the fixture based on a planogram.

Abstract: This application relates to systems and methods for automatically detecting and correcting image quality based on a set of quality standards. In some examples, a plurality of quality parameters of an image are determined based on receiving an image. It is then determined that at least one of the plurality of quality parameters is below a predetermined threshold. The predetermined threshold may be based on a required quality standard for images. In response to determining that the at least one of the plurality of quality parameters is below the predetermined threshold, feature of the image is adjusted such that the at least one of the plurality of quality parameters is at or above the predetermined threshold.

Abstract: An system and a method for scoring products viewed by a user prior to making a purchase decision and also identify the products considered most before ultimately purchasing. The system uses sensors placed on the shelves to identify the item viewed before making a purchase decision and also track the time spent per decision. The tracking will allow viewed and ultimately bought scores and item similarity scores to be determined. The scores in conjunction with point-of-sale terminal data to identify times determinative of users' interest levels prior to a purchase. The system predicatively replenishes inventory of high interest items based on historical patterns of interest and historical point-of-sale terminal data.

Abstract: Based upon the transition information for all the retail stores, a determination is made of an average cluster retention score. The average cluster retention score is a measure of how many retail stores have moved from original to different existing sales clusters in the current sales period. When the average cluster retention score is below a predetermined threshold, a complete re-organization of the existing sales clusters is performed. When the average cluster retention score is above the predetermined threshold, a determination is made as to whether each retail store should be re-classified.

Abstract: The disclosed fraud risk scoring tool provides data-driven identification of potential fraud cases. A fraud risk score is determined based at least on a weighted sum of multiple metrics, where weights are determined based on precision or inverse variance and suspension propensity importance, which is indicative of variable importance. An exemplary method includes: receiving and aggregating transaction metrics across customer IDs to produce an aggregated transaction metric data set; determining, for each aggregated transaction metric in the aggregated transaction metric data set, a precision value, a suspension propensity importance, and a scoring weight based at least on one of the precision value and the suspension propensity importance; determining, for each customer ID within the plurality of customer IDs, a risk score based at least on the scoring weights applied to corresponding transaction metrics and a risk priority; and reporting at least one customer ID associated with a selected risk priority.

Abstract: Initial sales cluster is divided by the control circuit into a plurality of velocity buckets. Subsequently, each velocity bucket is divided into a plurality of micro-clusters. The micro-clusters are defined according to demographic information or store characteristic information. A importance score and a performance score for each of the micro-clusters is determined. An optimal sales cluster and a corresponding optimal planogram for each retail store in each micro-cluster are determined based upon the importance score and the performance score.

Abstract: Approaches are provided that determine and fine-tune product assortments carried by retail stores. In aspects, the number of stores that carry the item, the sales performance of the item, the loyalty of customers to the item, whether substitutes for the item can be found, and other factors are used to determine an actions such as increasing or decreasing the shelf space for an item.

Abstract: Systems and methods for generating a hierarchical data structure are provided. An example method can include: acquiring sales data associated with items and item pairs in a category for a given period; filtering, based on a set of predetermined criteria, the sales data to obtain the items and the item pairs; generating document term matrices for the item pairs based on item description and item attributes; calculating attribute similarity measures and substitutability measures for the item pairs; performing, based on a set of predefined CBT generating rules, a hierarchical clustering on the document term matrices, item association, the substitutability measures and the attribute similarity measures; generating the CBT with a hierarchical grouping of the items; transforming the CBT to a dendrogram; pruning the dendrogram to generate a wireframe; regrouping the item pairs in CBT nodes with similar and substitutable attributes; and generating a user interface to visualize the CBT.

Abstract: The disclosed anomaly identification tool for fraud detection provides a data-driven method to identify potential fraud cases and includes receiving sales and refund data from transaction nodes, determining a plurality of metric data sets, for example return amount, return frequency, and return rate; and determining statistical distributions for the metrics. Risk thresholds can be set for identifying anomalous transactions, based on the metric statistics, which can be used as triggers for reporting risk or detection of potentially fraudulent transactions. Data analytics is thus leveraged, and can be applied at different levels and contexts of enterprise activity, for example by regions, by product line, and down to more focused areas such as specific retail channels. Some examples are able to identify anomalous activity indicative of collusion in fraudulent transactions.

Abstract: The disclosed fraud risk scoring tool provides data-driven identification of potential fraud cases. A fraud risk score is determined based at least on a weighted sum of multiple metrics, where weights are determined based on precision or inverse variance and suspension propensity importance, which is indicative of variable importance. An exemplary method includes: receiving and aggregating transaction metrics across customer IDs to produce an aggregated transaction metric data set; determining, for each aggregated transaction metric in the aggregated transaction metric data set, a precision value, a suspension propensity importance, and a scoring weight based at least on one of the precision value and the suspension propensity importance; determining, for each customer ID within the plurality of customer IDs, a risk score based at least on the scoring weights applied to corresponding transaction metrics and a risk priority; and reporting at least one customer ID associated with a selected risk priority.

Abstract: Examples a system for customized travel planning management. The system extracts relevant travel-related data from travel-related provider contracts. The extracted relevant travel-related data and historical travel usage data are analyzed to calculate a market share for each provider. A booking manager identifies recommended travel-related provider pairs associated with a set of travel dates within a predetermined range of a user-selected preferred date of travel associated with a user-selected source-to-destination pair based on the calculated market share for each provider and user-provided travel preferences. The system books the user's selected accommodations provider and travel provided on a recommended booking date. An optimization component identifies recommended future negotiation terms associated with at least one provider in the set of travel-related providers based on the historical travel usage data, historical transaction data and historical contract compliance data.

Abstract: Systems and methods for auto-naming nodes in a behavior tree are provided. An example method can include: providing a hierarchy of tree nodes by a computing device; generating a first corpus for each node at a final level; creating a first term-document matrix associated with the first corpus; identifying a first group of high-frequency words in the first term-document matrix; removing the first group of the high-frequency words obtain a second corpus; creating a second term-document matrix based on each of a set of predefined rules; identifying a second group of high-frequency words to represent node names; selecting a best set of the predefined rules based on an automatic evaluation model; generating a node name by removing a duplicate word in each node; incorporating feedback to generate a predicted name for each node; and selecting a final name for each node from the predicted name and the generated node name.

Abstract: Systems and methods for generating a hierarchical data structure are provided. An example method can include: acquiring sales data associated with items and item pairs in a category for a given period; filtering, based on a set of predetermined criteria, the sales data to obtain the items and the item pairs; generating document term matrices for the item pairs based on item description and item attributes; calculating attribute similarity measures and substitutability measures for the item pairs; performing, based on a set of predefined CBT generating rules, a hierarchical clustering on the document term matrices, item association, the substitutability measures and the attribute similarity measures; generating the CBT with a hierarchical grouping of the items; transforming the CBT to a dendrogram; pruning the dendrogram to generate a wireframe; regrouping the item pairs in CBT nodes with similar and substitutable attributes; and generating a user interface to visualize the CBT.

Abstract: A method for computer modeling a retail environment includes: calculating a space elasticity for an item category in a retail store, using a constrained linear regression model; calculating a cross-space elasticity for the item category in the retail store, using a multiple non-linear regression model; generating a category space allocation for the item category in the retail store, using a non-linear multiple-constraint mixed integer optimization model, based on the space elasticity of the item category and the cross-space elasticity of the item category; and generating an electronic planogram for the retail store, based on the category space allocation of the item category.