International Business Machines Corporation

Roger Douglas Lederman

Pawan Raghunath Chowdhary

Markus Ettl

Zhengliang Xue

Chandrasekhar Narayanaswami

Herbert Scott McFaddin

Tim Nonner

Ulrich B Schimpel

Hongxia Yang

Laura Wynter

Chitra Dorai

Xu Sun

Rajesh Kumar Ravi

Adam N Elmachtoub

Zhenyu Hu

Thomas L Scheid

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 for controlling the timing of customer interactions (e.g., targeted product or service offerings to customers) in order to determine optimally efficient usage of a seller's available inventory are disclosed. A customer selection problem (CSP) may be formulated and solved to implement a customer selection policy for controlling the timing with which customers from a customer pool will be targeted with offerings. The customer selection policy may include dynamic optimization to account for intertemporal effects of customer decisions.

Revenue management using dynamic customer selection

A customer segmentation method, system, and computer program product, include inputting a set of characteristic features for each of a plurality of customers, defining a customer-event map that maps the characteristic features of each of the customers to a plurality of event categories, and estimating a likelihood of an event driven purchase for each product type and an event category combination.

Customer segmentation based on latent response to market events

A market event identification method, system, and computer program product, include defining a likelihood function that maps a likelihood of a purchase of a product during an event by customers having similar customer features and estimating a likelihood of an event-driven purchase by the customers for each of a plurality of product-event combinations using the defined likelihood function.

Market event identification based on latent response to market events

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

System, method and computer program product for effective supply-side planning of inventories during product transitions. The system for a supply-side entity that generates recommendations that include personalized shaping actions to control each customer's rate of adoption of a new product to replace an older legacy product during a transition period, and optimize overall use of available supply. The method optimizes personalized shaping actions so that a customer is transitioned at a speed that suits their personal profile as well as the seller's production/inventory constraints for each product. Shaping actions are determined based on the trajectory of each product's lifecycle. Further, customer-level adoption patterns for transitioning products are predicted from past behavior.

Balancing inventory by personalized transition planning

A method for projecting performance of a target asset compared to a benchmark, the method comprising receiving one or more target matrices corresponding to a target portfolio and one or more benchmark matrices corresponding to a benchmark portfolio, wherein the target matrices and benchmark matrices comprise elements corresponding to variables that influence portfolio performance trajectory, computing a target performance trajectory based on the one or more target matrices and a benchmark performance trajectory based on the benchmark matrices, identifying actions to bring the target performance trajectory above the benchmark performance trajectory; and communicating the identified actions.

Performance projection

A method and structure of estimating traffic in a network. A real-time estimate of the network traffic is calculated, based on limited real-time data about the network traffic calculated in an offline phase and limited real-time data received in a real-time phase.

Growing community of inventors

Briarcliff Manor, NY, United States of America

Roger Douglas Lederman