Oracle International Corporation

Su-Ming Wu

Kiran V Panchamgam

Setareh Borjian Boroujeni

Andrew Vakhutinsky

Aswin Kannan

Yevgeniy Popkov

Mark E Ferguson

Olga Pak

Olga Perdikaki

Robert F Corr

Peter Gaidarev

Sajith Vijayan

Z Maria Wang

Saraswati Yagnavajhala

Nikos Nikolakis

Mengzhenyu Zhang

Sandeep Tiwari

Manish Gupte

William M Warrick, Ii

Randall Fernandes

Stephen Clegg

Santosh Bai Reddy

Sajad Modaresi

Bernard Griffiths

Fernando Bernstein

Denis Saure

Systems, methods, and other embodiments associated with self-tuning optimization of a replenishment policy of an item are described. In one embodiment, the method includes determining an initial replenishment policy of the item. A performance of the initial replenishment policy is determined based upon past performance of the initial replenishment policy. The initial replenishment policy is revised to get a service level of the item for future sales periods closer to a target service level of the item. Information is forwarded in real-time about the revised replenishment policy to an order fulfillment facility.

System and method for self-tuning optimization of an item replenishment policy

Systems, methods, and other embodiments associated with computing and generating schedule data structures for items in a display are described. In one embodiment, a method includes accessing a sales data structure corresponding to a store and analyzing sales records for items associated with subcategories to calculate a subcategory profit contribution score for each subcategory. The method may also include selecting a first subcategory from the subcategories as a candidate subcategory of items and analyzing the sales records to calculate an item profit contribution score for each of the items assigned to the candidate subcategory. A first item is selected from the candidate subcategory to be placed on a promotional display space, based upon the item profit contribution score of the first item. A schedule data structure is generated that assigns the first item to the promotional display space.

Method and system for generating a schedule data structure for promotional display space

Embodiments detect fraud of risk targets that include both customer accounts and cashiers. Embodiments receive historical point of sale ('POS') data and divide the POS data into store groupings. Embodiments create a first aggregation of the POS data corresponding to the customer accounts and a second aggregation of the POS data corresponding to the cashiers. Embodiments calculate first features corresponding to the customer accounts and second features corresponding to the cashiers. Embodiments filter the risk targets based on rules and separate the filtered risk targets into a plurality of data ranges. For each combination of store groupings and data ranges, embodiments train an unsupervised machine learning model. Embodiments then apply the unsupervised machine learning models after the training to generate first anomaly scores for each of the customer accounts and cashiers.

Artificial intelligence based fraud detection system

Systems, methods, and other embodiments associated with generating a price schedule are described. In one embodiment, for each customer segment of a plurality of customer segments, a per-segment value of an approximate objective function for the customer segment is determined by an optimizer, and a ratio of the per-segment value to a sum of all per-segment values for the customer segments is computed. The inventory quantity is allocated amongst the customer segments according to the ratio for each customer segment to form an inventory quantity for each customer segment. For each customer segment, a promotion portion of the price schedule that maximizes the objective function by the optimizer is determined. A quantity of remaining inventory allocated to the plurality of customer segments at an end of the regular season is aggregated. A markdown portion of the price schedule for the item that maximizes the objective function is determined by the optimizer. The promotion portion and the markdown portion are combined to create the price schedule for the item.

Computerized promotion and markdown price scheduling

Systems, methods, and other embodiments associated with controlling inventory depletion by offering different prices to different customers are described. In one embodiment, a method includes establishing first and second allocations of fulfillment centers to different geographic regions during a markdown phase. Different price schedules are determined for the orders to be fulfilled during the markdown phase based on the first and second allocations. A predicted profit is generated for the orders fulfilled under each of the different price schedules. A price schedule corresponding to the first allocation is selected as resulting in a greater predicted profit than another one of the different price schedules. A sale terminal is controlled to enact the selected price schedule during the markdown phase to cause fulfillment of the incoming orders according to the first allocation of the fulfillment centers.

System and method for controlling inventory depletion by offering different prices to different customers

One example of computerized inventory redistribution control includes, for each location inventory record in a set of location inventory records, calculating a quantity change that will bring a current item quantity to a different item quantity for the location inventory record. Determining a cost of a minimum-cost redistribution among the physical locations to effect the quantity changes. Determining a scaling factor that maximizes total revenue when the quantity changes are scaled by the scaling factor after deducting the cost scaled by the scaling factor. Generating transfer instructions for a redistribution of the item by scaling the transfer quantities of the minimum-cost redistribution by the scaling factor. Transmitting each transfer instruction to a computing device associated with a physical location indicated in the transfer instruction.

Computerized inventory redistribution control system

Systems, methods, and other embodiments associated with incrementally swapping items in an assortment are described. In one embodiment, a computing system includes demand logic configured to read data from an electronic data structure that defines an assortment. The assortment defines a subset of items from a product category. The demand logic is configured to generate forecasted changes to an associated metric value by generating demand transference values for (i) individually removing each item presently in the assortment and (ii) individually adding each item of a set of available items of the product category. The computing system includes assortment logic configured to transform the electronic data structure that defines the assortment according to the forecasted changes by incrementally swapping items in the assortment for new items in the available set of items until the forecasted changes between items in the assortment and new items in the set of available items satisfy a predefined condition.

Assortment optimization using incremental swapping with demand transference

Embodiments determine a price schedule for an item by, for each item, receiving a set of prices for the item, an inventory quantity for the item, a per-segment demand model for the item, and an objective function that is a function of the per-segment demand model and maximizes revenue based at least on a probability of a return of the item and a cost of the return. Embodiments allocate the inventory quantity among a plurality of customer segments based at least on a predicted contribution of each customer segment to the objective function. Embodiments determine a markdown portion of the price schedule for the item that maximizes the objective function, where the markdown portion assigns a series of prices selected from the set of prices for respective time periods during a clearance season for the item.

Price optimization system

Embodiments provide a recommendation for an additional item in response to receiving a basket of goods determine a type for the basket of goods from a set of basket types, receive a set of additional targeted items as target recommendations and receive a history of received types of baskets of goods. Embodiments iteratively perform a clustering into a plurality of clusters of each of the basket types based on the history of received types of baskets of goods, and preference updating for each of the targeted items into each of the plurality of clusters. The iteratively performing, after a plurality of iterations, outputs a sequence of mappings and a sequence of preference parameters. Embodiments generate a frequency of tabulation of mappings from the sequence of mappings and then generate the recommendation based on the sequence of mappings, the sequence of preference parameters and the frequency of tabulation of mappings.

Quick learning recommendation method, non-transitory computer readable medium and system for baskets of goods

Systems, methods, and other embodiments associated with extracting attributes from electronic data structures are described. In one embodiment, a method includes correlating tokens from description strings with defined attributes in an electronic inventory database by identifying which of the defined attributes match the tokens to link the tokens with columns of the database associated with the defined attributes. The method includes iteratively updating annotation strings for unidentified ones of the tokens by generating suggested matches for the unidentified tokens according to known correlations between identified tokens and the defined attributes using a conditional random fields model. The method also includes populating the database using the identified tokens from the description strings according to the annotation strings by automatically storing the tokens from the description strings into the columns as identified by the annotation strings.

Annotation system for extracting attributes from electronic data structures

Systems, methods, and other embodiments associated with attribute redundancy removal are described. In one embodiment, a method includes identifying redundant attribute values in a group of attributes that describe two items. The example method also includes generating a pruned group of attributes having the redundant attribute values removed. The similarity of the two items is calculated based, at least in part, on the pruned group of attribute values.

Attribute redundancy removal

Systems, methods, and other embodiments associated with generating a price schedule are described. A inventory quantity for the item is allocated amongst a plurality of customer segments based at least on a predicted contribution of each customer segment to the objective function. For each customer segment, based at least on a quantity of inventory allocated to the customer segment, a promotion portion of the price schedule is determined that maximizes the objective function. A quantity of remaining inventory allocated to the plurality of customer segments at the end of the regular season is aggregated. Based at least on the aggregated inventory, a markdown portion of the price schedule for the item is determined that maximizes the objective function. The promotion portion and the markdown portion are combined to create a price schedule for the item.

Systems, methods, and other embodiments associated with forecasting customer channel choice using cross-channel loyalty are described. In one embodiment, a method includes accessing historical values for each of one or more loyalty variables for respective customers. The method also includes determining respective loyalty variable predictors for each of the one or more loyalty variables for each customer based on the historical values. In response to a trigger event associated with a given customer, the loyalty variable predictors for the customer are used to estimate a present value of each of the one or more loyalty variables for the customer. The present value of each of the loyalty variables is input to a forecast model that calculates, for each channel, a probability that the customer will make a purchase using the channel. The purchase probabilities are provided for use in selecting a marketing message for the customer.

Forecasting customer channel choice using cross-channel loyalty

A system generates a consumer decision tree ('CDT'). The system receives customer purchasing data that includes transactions of a plurality of products each having at least one product attribute. For a product category, the system identifies a plurality of similar products from the purchasing data and one or more attributes corresponding to each similar product. The system assigns the product category as a current level of the CDT, and determines a most significant attribute of the plurality of attributes for the current level. The system forms a next level of the CDT by dividing the most significant attribute into a plurality of sub-sections, where each sub-section corresponds to an attribute value of the most significant attribute. The system then forms a next level of the CDT for each sub-section until a terminal node is identified.

Growing community of inventors

Waltham, MA, United States of America

Su-Ming Wu