International Business Machines Corporation

Markus Ettl

Karthik Sourirajan

Zhengliang Xue

Pawan Raghunath Chowdhary

Young Min Lee

Feng Cheng

Thomas Robert Ervolina

Daniel Patrick Connors

David D Yao

Rajesh Kumar Ravi

Hongxia Yang

Soumyadip Ghosh

Anshul Sheopuri

Pavithra Harsha

Pu Huang

Shivaram Subramanian

Lianjun An

Roger Douglas Lederman

Grace Yuh-Jiun Lin

Rui Zhang

Amit Dhurandhar

Shubir Kapoor

Daniel John Peters

Sechan Oh

Grace Y Lin

Tim Nonner

Ulrich B Schimpel

Donald Keefer

David Da-Wei Yao

Laurence Allan Phillips

Gabriel Toma

Bruce C Graves

Erik Rueger

Thorsten Muehge

Yu Tang

Aliza Rivka Heching

Mary Elizabeth Helander

Wei Sun

Stuart A Siegel

Ching-Hua Chen-Ritzo

Mamnoon Jamil

Marek Petrik

Robert James Wittrock

Gerald E Feigin

John Peter Fasano

Anthony T Mazzatti

William Stephen Schaefer

Adam N Elmachtoub

Blair A Binney

Yadav P Singh

Roman Kapuscinski

Zhenyu Hu

David Da-Wel Yao

Gopikrishna Maniachari

Beverley Joanne Dyke

Steven G Pinchuk

Thomas William Moncreaff

Somnath Mukherjee

The present disclosure relates to a method for classifying a non-monetary donation. The method comprises: training a machine learning model comprising input neurons arranged in an input layer, each input neuron being operable for inputting an input value (X) of a parameter of the donation, and at least one hidden layer comprising multiple hidden neurons, each hidden neuron being operable for calculating a hidden layer value based on at least one input value and weights (w(X, Y)) associated with the respective input neurons. The number of input parameters may be reduced based on ranking the weights (w(X, Y)) related to the individual input parameters. The number of neurons of the hidden layer may be reduced based on ranking the weights related to the individual neurons of the hidden layer. The trained model, the reduced input parameters, and reduced hidden neurons may be provided for enabling the classification using the trained model.

Classification of a non-monetary donation based on machine learning

A method for planning under uncertainty is disclosed. The method includes steps of processing a stochastic programming formulation based on forecast values of at least one of product and service configurations, and determining a resource requirements plan for one or more planning periods in a non-deterministic bill of resources of at least two levels.

Method and structure for risk-based resource planning for configurable products

Systems, methods, and computer-readable media are disclosed for identifying customers having associated opportunities for improved growth and/or profitability with respect to product or service offerings and determining investment solutions that enhance the probability that the customers transition to the higher growth/profitability opportunities. Prior customer transactions are segmented based on segmentation criteria and used to generate a transaction graph. The nodes of the transaction graph represent the segmented transactions and client transaction paths between the nodes represent potential customer life-cycle trajectories. The transaction graph can be used to identify high-value penetration opportunities.

Dynamic management of a customer life-cycle value

A computer generates an optimized decision distribution vector for a plurality of related, demand-correlated products. The computer receives data indexed by product, with each entry including several entry attributes. The computer receives decision context data for the products. The computer determines a set of primary attributes and trains a first machine learning model based upon those attributes. The computer receives a decision optimization request that includes an associated set of attributes corresponding to the primary attributes. The computer scores the associated set of attributes, using the first machine learning model, to generate a baseline purchase propensity. The computer trains a second machine learning model, based upon the baseline purchase propensity and the decision context data, to generate own-product and cross-product elasticity data. The computer, using the own-product and cross-product elasticity data, generates a decision distribution vector for the group of related, demand-correlated products.

Automated hybrid propensity decision vector generation using artificial intelligence

A machine learning algorithm is trained to learn to cluster a plurality of original-destination routes in a network for transporting cargo into a plurality of clusters based on similarities of the original-destination routes, and to learn to cluster the plurality of clusters into a plurality of subgroups based on customer behavior. Influencing criteria associated with each of the subgroups may be determined and based on the influencing criteria, a price elasticity curve for each of the subgroups may be generated. Based on the price elasticity curve and current network traffic, cargo transportation price associated with each of the subgroups may be determined.

Training a machine to automate spot pricing of logistics services in a large-scale network

Systems, methods, and computer-readable media are disclosed for identifying product configurations that are alternatives to a requested product configuration, ranking the alternative product configurations based on one or more pricing metrics, and presenting the alternative product configurations to a prospective customer, thereby providing the customer with the option of selecting an alternative product configuration in lieu of the initially requested product configuration.

Product configuration recommendation and optimization

A system that compresses data during neural network training. A memory stores computer executable components and neural network data, and a processor executes computer executable components stored in the memory. An anticipatory value of inventory (VOI) optimization component calculates optimal VOI and prices for immediate-future inventory levels in parallel and writes latest price updates for respective states to a price stack; and a recommendation component provides customized pricing recommendation for a product relative to a unique customer as a function of the latest price updates for respective states to the price stack.

Real time personalized pricing for limited inventory assortments in a high-volume business environment

System and method that improves cargo logistics may be presented. For instance, shipping capacity in cargo logistics may be best utilized based on providing pricing and scheduling solutions that are jointly optimized and prices differentiated based on flexibility of service request. Scheduled service and pricing may be transmitted as a signal to control execution of the cargo logistics.

Cargo logistics dispatch service with integrated pricing and scheduling

A system, method and computer program product for determining a target population to be subject to a promotion or offer of goods/services. The target population is determined that strongly prefers a given promotion, while also making sure the target population represents a sizable number of consumers such that profits may be maximized. The system provides an output solution listing available promotion options and one or more corresponding target groups based on solving an optimization problem that incorporates, prior obtained most important customer features for each promotion using historical promotion data and statistics measures. The system may automatically initiate a promotion offering to each of said customers by communicating the promotion to the members of the targeted group of people, wherein a percentage of future transactions to which the promotion is offered is expected to exceed a threshold level.

Determining feature importance and target population in the context of promotion recommendation

An apparatus, method and computer program product for identifying fraud in transaction data. The method includes: receiving invoice data comprising a vendor, a requestor and events, receiving public data and private data sources, computing a vendor risk score using the public and private data sources matching the vendor of the invoice data, computing a requestor risk score using the public data sources and the private data sources matching the requestor of the invoice data, computing an active invoice score using the vendor risk score and the requestor risk score and when the active invoice score is greater than a predetermined amount, blocking the invoice data. In one embodiment, computing a vendor risk score comprises obtaining a weight and a confidence for the event, calculating an event vendor risk score using the weight times the confidence and combining the event vendor risk scores for all of the events.

Ranking and tracking suspicious procurement entities

An algebra and differential equations model of a physical system is constructed based on available training data and physical system characteristics. A hybrid calibration process is carried out to iteratively calibrate both time-insensitive and time-sensitive parameters of the algebra and differential equations model so as to obtain parameter vectors. Vector auto-regression is applied to the parameter vectors to predict values of the parameters for a future time period.

Building thermal control techniques

User information may be received and a market segment associated with the user may be received. A personalized or individualized offer may be determined based on the user information, the personalized offer determined based on a product offeror's goal with respect to the user at a given time. The market segment offer and the personalized offer may be blended to determine a recommended personalized offering for the user at the given time, e.g., given a company's tactical, strategic and lifetime goals and values for that user.

Computer-implemented techniques for determining and provisioning real-time individualized product and service offering

Growing community of inventors

Ossining, NY, United States of America

Markus Ettl