Abstract: The disclosed embodiments provide a system that detects sensor anomalies in a univariate time-series signal. During a surveillance mode, the system receives the univariate time-series signal from a sensor in a monitored system. Next, the system performs a staggered-sampling operation on the univariate time-series signal to produce N sub-sampled time-series signals, wherein the staggered-sampling operation allocates consecutive samples from the univariate time-series signal to the N sub-sampled time-series signals in a round-robin ordering. The system then uses a trained inferential model to generate estimated values for the N sub-sampled time-series signals based on cross-correlations with other sub-sampled time-series signals. Next, the system performs an anomaly detection operation to detect incipient sensor anomalies in the univariate time-series signal based on differences between actual values and the estimated values for the N sub-sampled time-series signals.

Abstract: A processor may receive a request for a query item may include a plurality of identifying markers, relating to data associated with the query item. A machine learning model, trained to identify similar items according to the plurality of identifying markers, may then process the plurality of identifying markers and provide a list of one or more similar items and respective similarity distances. The processor may access a respective entity profile including one or more scenario scores for each of the similar items. The processor may then calculate an entity score for each respective entity profile using the respective similarity distances and the scenario scores. The processor may then generate an entity list by ranking the respective entities associated with each respective entity profile using the entity score. The processor may then output the entity list to the client device.

Abstract: A processor may receive a request for a query item may include a plurality of identifying markers, relating to data associated with the query item. A machine learning model, trained to identify similar items according to the plurality of identifying markers, may then process the plurality of identifying markers and provide a list of one or more similar items and respective similarity distances. The processor may access a respective entity profile including one or more scenario scores for each of the similar items. The processor may then calculate an entity score for each respective entity profile using the respective similarity distances and the scenario scores. The processor may then generate an entity list by ranking the respective entities associated with each respective entity profile using the entity score. The processor may then output the entity list to the client device.

Abstract: The disclosed embodiments provide a system that detects sensor anomalies in a univariate time-series signal. During a surveillance mode, the system receives the univariate time-series signal from a sensor in a monitored system. Next, the system performs a staggered-sampling operation on the univariate time-series signal to produce N sub-sampled time-series signals, wherein the staggered-sampling operation allocates consecutive samples from the univariate time-series signal to the N sub-sampled time-series signals in a round-robin ordering. The system then uses a trained inferential model to generate estimated values for the N sub-sampled time-series signals based on cross-correlations with other sub-sampled time-series signals. Next, the system performs an anomaly detection operation to detect incipient sensor anomalies in the univariate time-series signal based on differences between actual values and the estimated values for the N sub-sampled time-series signals.

Abstract: Systems, methods, and machine-readable media are disclosed to allocating inventory across a plurality of locations in a supply chain. In one embodiment, a method comprises determining a total time-phased inventory and target safety stock level for each of the items at each location based on the baseline inventory as determined from expected demand and lead times for each item at each location, a target service level, a demand uncertainty level, a lead time uncertainty level, carrying costs in the supply chain and user constraints on budget, capacity and inventory.

Abstract: Systems and methods in accordance with various embodiments of the present invention provide for a system and method for simultaneous price optimization and asset allocation to maximize manufacturing profits. In one embodiment, a set of price points for the item and a set of expected demand values for each price point are determined. A supply-side constraint which models inventory, replenishment, and capacities associated with replenishment and a joining constraint, which requires that the set of expected demand values be equal to a planned supply of the item, are determined. A demand-side constraint is determined. Further, an objective function to maximize profits is determined, based on the set of price points, the set of expected demand values, and subject to the supply-side, joining, and demand-side constraints. Based on the objective function, an optimal price profile for the item is provided.

Abstract: Systems and methods in accordance with various embodiments of the present invention provide for a system and method for simultaneous price optimization and asset allocation to maximize manufacturing profits. In one embodiment, a set of price points for the item and a set of expected demand values for each price point are determined. A supply-side constraint which models inventory, replenishment, and capacities associated with replenishment and a joining constraint, which requires that the set of expected demand values be equal to a planned supply of the item, are determined. A demand-side constraint is determined. Further, an objective function to maximize profits is determined, based on the set of price points, the set of expected demand values, and subject to the supply-side, joining, and demand-side constraints. Based on the objective function, an optimal price profile for the item is provided.

Abstract: Systems, methods, and machine-readable media are disclosed to allocating inventory across a plurality of locations in a supply chain. In one embodiment, a method comprises determining a total time-phased inventory and target safety stock level for each of the items at each location based on the baseline inventory as determined from expected demand and lead times for each item at each location, a target service level, a demand uncertainty level, a lead time uncertainty level, carrying costs in the supply chain and user constraints on budget, capacity and inventory.