Abstract: Mechanisms are provided for generating a resource allocation in an omnichannel distribution network. Demand forecast data and current inventory data related to a resource and the omnichannel distribution network are obtained and an ally-adversary bimodal inventory optimization (BIO) computer model is instantiated that includes an adversary component that simulates, through a computer simulation, a worst-case scenario of resource demand and resource availability, and an ally component that limits the adversary component based on a simulation of a limited best-case scenario of resource demand and resource availability. The BIO computer model is applied to the demand forecast data and current inventory data, to generate a predicted consumption for the resource. A resource allocation recommendation is generated for allocating the resource to locations of the omnichannel distribution network based on the predicted consumption, which is output to a downstream computing system for further processing.

Abstract: An example operation may include one or more of storing a hierarchical data set, receiving a plurality of predicted outputs from a plurality of nodes in a distributed computing environment, respectively, wherein each predicted output is generated by a different node via execution of a time-series forecasting model on a different subset of lowest level data in the hierarchical data set, combining the plurality of predicted outputs via bottom-up aggregation to generate one or more additional predicted outputs for the time-series forecasting model based on one or more levels above the lowest level in the hierarchical time-series data set, determining error values for the time-series forecasting model at each level of the hierarchical data set based on the received and the one or more additional generated predicted outputs, and modifying a parameter of the time-series forecasting model based on the determined error values.

Abstract: An example operation may include one or more of acquiring, by a retailer node, an inventory data from a supplier node over a blockchain network, receiving, by the retailer node, outstanding orders data of the supplier node, generating, by the retailer node, an order distribution policy based on the inventory data and the outstanding orders data, and executing a smart contract to order goods from the supplier node based on the ordering policy.

Abstract: An example operation may include one or more of storing a hierarchical time-series data set in memory, initially training a first time-series forecasting model based on a lower level of time-series data in the hierarchical data set, training a second time-series teaching forecasting model based on an upper level of time-series data from the hierarchical data set which includes an additional level of aggregation with respect to the lower level of time-series data, optimizing one or more parameters of the initially trained first time-series forecasting model based on predicted outputs from the trained second time-series forecasting model in comparison to predicted outputs from the initially trained first time-series forecasting model, and storing the modified first time-series forecasting model in the memory.

Abstract: An example operation may include one or more of acquiring, by a retailer node, an inventory data from a supplier node over a blockchain network, receiving, by the retailer node, outstanding orders data of the supplier node, generating, by the retailer node, an order distribution policy based on the inventory data and the outstanding orders data, and executing a smart contract to order goods from the supplier node based on the ordering policy.

Abstract: An example operation may include one or more of receiving, by a first node, a freshness of goods data from a second node over a blockchain, and executing, by the first node, a smart contract to: calculate an initial order quantity based on a pre-set critical order number and a non-expiring goods order quantity and alter a final order quantity based on the initial order quantity and the freshness of the goods data.

Abstract: An example operation may include one or more of receiving, by a retailer node, an encrypted inventory of goods data from a plurality of supplier nodes over a blockchain network, computing, by the retailer node, an ordering proportion based on the encrypted inventory of goods data, generating, by the retailer node, an ordering policy based on the ordering proportion, and executing a smart contract to order goods from the plurality of the supplier nodes based on the ordering policy.

Abstract: An example operation may include one or more of receiving, by a retailer node, an encrypted inventory of goods data from a plurality of supplier nodes over a blockchain network, computing, by the retailer node, an ordering proportion based on the encrypted inventory of goods data, generating, by the retailer node, an ordering policy based on the ordering proportion, and executing a smart contract to order goods from the plurality of the supplier nodes based on the ordering policy.

Abstract: A processor may estimate uncensored demand from historical supply chain data. The processor may ingest historical data. The processor may convert the historical data to a dataset of multiple time series corresponding to sales for different products and locations and channels across multiple time points that is usable by an uncensored demand estimation machine learning model. The processor may train the uncensored demand estimation machine learning model by applying optimization solver techniques for deep learning.

Abstract: A processor in an omnichannel environment, over a specific network with transaction level operations, may receive one or more input configurations. The processor may identify, based on the one or more input configurations, one or more articles. The processor may identify one or more key performance indicators (KPIs) associated with the one or more articles. The processor may compute, based on an uncensored demand trajectory, an impact on the KPIs over a specified period in the omnichannel environment. The processor may provide the impact to a user.

Abstract: In an approach to improve order management by performing sustainable order fulfillment optimization through computer analysis, embodiments receive an order from a user through the order management system for performing sustainable order fulfillment. Further, embodiments estimate carbon emissions and economic costs of fulfilling the order from a plurality of nodes, and output an optimal sustainable order fulfillment. Additionally, responsive to receiving confirmation to implement the output optimal sustainable order fulfillment, embodiments place the optimal sustainable order fulfillment for the received order.

Abstract: In an aspect, input data can be received, including at least time series data associated with purchases of at least one product and causal influencer data associated with the purchases. The causal influencer data can include at least non-stationary data, where lost shares associated with said at least one product are unobserved. An artificial neural network can be trained based on the received input data to predict a future global demand associated with at least one product and individual market shares associated with at least one product. The artificial neural network can include at least a first temporal network to predict the global demand and a second temporal network to predict each of the individual market shares. The first temporal network and the second temporal network can be trained simultaneously.

Abstract: An example operation may include one or more of receiving, by a retailer node, an encrypted inventory of goods data from a plurality of supplier nodes over a blockchain network, computing, by the retailer node, an ordering proportion based on the encrypted inventory of goods data, generating, by the retailer node, an ordering policy based on the ordering proportion, and executing a smart contract to order goods from the plurality of the supplier nodes based on the ordering policy.

Abstract: A computer implemented method of improving parameters of a critic approximator module includes receiving, by a mixed integer program (MIP) actor, (i) a current state and (ii) a predicted performance of an environment from the critic approximator module. The MIP actor solves a mixed integer mathematical problem based on the received current state and the predicted performance of the environment. The MIP actor selects an action a and applies the action to the environment based on the solved mixed integer mathematical problem. A long-term reward is determined and compared to the predicted performance of the environment by the critic approximator module. The parameters of the critic approximator module are iteratively updated based on an error between the determined long-term reward and the predicted performance.

Abstract: An example operation may include one or more of receiving, by a retailer node, an encrypted inventory of goods data from a plurality of supplier nodes over a blockchain network, computing, by the retailer node, an ordering proportion based on the encrypted inventory of goods data, generating, by the retailer node, an ordering policy based on the ordering proportion, and executing a smart contract to order goods from the plurality of the supplier nodes based on the ordering policy.

Abstract: An example operation may include one or more of collecting, by a first node, a plurality of permissioned data inputs from a plurality of second nodes of a supply-chain, performing, by the first node, a granular simulation based on the permissioned data inputs to generate a plurality of key performance indicators (KPIs), and executing a smart contract to adjust order processes of the supply-chain based on the KPIs.

Abstract: An example operation may include one or more of acquiring, by a retailer node, an inventory data from a supplier node over a blockchain network, receiving, by the retailer node, outstanding orders data of the supplier node, generating, by the retailer node, an order distribution policy based on the inventory data and the outstanding orders data, and executing a smart contract to order goods from the supplier node based on the ordering policy.

Abstract: A machine learning system that uses a split net configuration to incorporate arbitrary constraints receives a set of input data and a set of functional constraints. The machine learning system jointly optimizes a deep learning model by using the set of input data and a wide learning model by using the set of constraints. The deep learning model includes an input layer, an output layer, and an intermediate layer between the input layer and the output layer. The wide learning model includes an input layer and an output layer but no intermediate layer. The machine learning system provides a machine learning model comprising the optimized deep learning model and the optimized wide learning model.

Abstract: A machine learning system that incorporates arbitrary constraints is provided. The machine learning system selects a set of domain-specific constraints from a plurality of sets of domain-specific constraints. The machine learning system selects a set of general functional relationships from a plurality of sets of general functional relationships. The machine learning system maps the selected set of general functional relationships and the selected set of domain-specific constraints to a set of learning transforms. The machine learning system modifies a machine learning specification according to the set of learning transforms, wherein the machine learning specification specifies a model construction, a model setup, and a training objective function. The machine learning system optimizes a machine learning model according to the modified machine learning specification.

Abstract: A machine learning system that incorporates arbitrary constraints into deep learning model is provided. The machine learning system provides a set of penalty data points en a set of arbitrary constraints in addition to a set of original training data points. The machine learning system assigns a penalty to each penalty data point in the set of penalty data points. The machine learning system optimizes a machine learning model by solving an objective function based on an original loss function and a penalty loss function. The original loss function is evaluated over a set of original training data points and the penalty loss function is evaluated over the set of penalty data points. The machine learning system provides the optimized machine learning model based on a solution of the objective function.