Abstract: An Artificial Intelligence (AI)-based attribute prediction system generates predictions for attributes of highly customized equipment in response to received user requests. Processed historical data is initially used to generate feature combinations which are then employed along with a plurality of statistical and machine learning (ML) models in order to identify a best scoring model-feature combination in two selection cycles using multiple selection criteria. The predictions for an attribute are generated by the best scoring model and feature combination. Various insights regarding the features affecting the attribute can be additionally derived to provide recommendations to the user.

Abstract: A material failure forecasting system accesses historical failure data to forecasts future failures. The failure data of a material is analyzed using text processing techniques to identify failures and suspensions. The text processing techniques provide for identifying failures when fault words are associated with negations. A fault ontology establishes different failure modes that include primary, secondary and tertiary levels which enable identifying a sequence of failures. The failures thus identified are fitted to a data distribution selected from a plurality of data distributions. The parameters from the data distribution are used for simulating a demand profile for the material which considers interchangeability. Similarly failure data of the materials in an equipment can be analyzed and the reliability of the equipment can be estimated.

Abstract: A material failure forecasting system accesses historical failure data to forecasts future failures. The failure data of a material is analyzed using text processing techniques to identify failures and suspensions. The text processing techniques provide for identifying failures when fault words are associated with negations. A fault ontology establishes different failure modes that include primary, secondary and tertiary levels which enable identifying a sequence of failures. The failures thus identified are fitted to a data distribution selected from a plurality of data distributions. The parameters from the data distribution are used for simulating a demand profile for the material which considers interchangeability. Similarly failure data of the materials in an equipment can be analyzed and the reliability of the equipment can be estimated.

Abstract: A machine learning (ML) based intermittent data processing system accesses a collection of intermittent data points, determines a data distribution associated with the collection and generates one or more calculated values based on the data distribution. A simulation can be employed to determine the accuracy of the calculated values based on which, the calculated values can be employed for further processing. The collection of intermittent data points is initially processed to determine if one or more of the data distribution identification, bootstrapping or variability capping techniques are to be applied in order to obtain the calculated values. The calculated values are used to generate visualizations and recommendations.

Abstract: An Artificial Intelligence (AI)-based attribute prediction system generates predictions for attributes of highly customized equipment in response to received user requests. Processed historical data is initially used to generate feature combinations which are then employed along with a plurality of statistical and machine learning (ML) models in order to identify a best scoring model-feature combination in two selection cycles using multiple selection criteria. The predictions for an attribute are generated by the best scoring model and feature combination. Various insights regarding the features affecting the attribute can be additionally derived to provide recommendations to the user.

Abstract: A machine learning (ML) based intermittent data processing system accesses a collection of intermittent data points, determines a data distribution associated with the collection and generates one or more calculated values based on the data distribution. A simulation can be employed to determine the accuracy of the calculated values based on which, the calculated values can be employed for further processing. The collection of intermittent data points is initially processed to determine if one or more of the data distribution identification, bootstrapping or variability capping techniques are to be applied in order to obtain the calculated values. The calculated values are used to generate visualizations and recommendations.

Abstract: A method and system is provided for mitigating risk in a supply chain. The present application provides a method and system for mitigating risk in a multi echelon stochastic flexible supply chain, comprises categorizing a plurality of supply chain risks pertaining into a plurality of supply chain risk sub categories; developing a risk decision model for each of the plurality of supply chain risk sub categories; extracting supply chain risk information from a plurality of information sources including a plurality of social media information sources; validating, customizing and estimating social media risk score for each of the plurality of supply chain risk sub categories; integrating estimated social media risk score for each of the plurality of supply chain risk sub categories for each supply chain member; and utilizing consolidated social media risk score in the developed risk decision model for mitigating risk.

Abstract: This disclosure relates generally to computation of credit scores, and more particularly to methods and devices for computing optimized credit scores. A computer implemented method for computing optimized credit scores comprises transmitting a data retrieval request to a data source for retrieving profile data associated with a plurality of individuals. Availability of social media data for each individual is ascertained based on corresponding profile data. Each of the plurality of individuals is classified into a first set and second set based on the availability of the social media data associated with the individual. A social media score for each individual present in the first set is determined. A social media score for each individual present in the second set is determined based on social media scores of the first set. A credit score for each individual is determined based on corresponding social media score of the individual.