Abstract: Embodiments for ensemble policy generation for prediction systems by a processor. Policies are generated and/or derived for a set of ensemble models to predict a plurality of target variables for streaming data such that the plurality of policies enables dynamic adjustment of the prediction system. One or more of the policies are updated according to one or more error states of the set of ensemble models.

Abstract: Embodiments for self-managed adaptable models for prediction systems by one or more processors. One or more adaptive models may be applied to data streams from a plurality of data sources according to one or more data recipes such that the one or more adaptive models predict a plurality of target variables.

Abstract: Performing data clustering in a model property vector space. Input data is received comprising a plurality of data instances in a data vector space. A model property vector specification is defined for a model vector. Information is identified from the input data, and a model property vector is created in the model property vector space for each of the plurality of data instances. A target number of clusters is identified and used to perform a data clustering procedure. An output is generated comprising a plurality of data segments and one or more clustering rules. For each data cluster, a predictive model is constructed for each data segment of the plurality of data segments.

Abstract: Embodiments for network reconstruction from message data by a processor. A digital map may be created using one or more messages of a plurality of vehicles obtained at a plurality of control points of a route network. The digital map may be analyzed to estimate a feasibility of simultaneous trajectories of the plurality of vehicles between selected locations in the route network.

Abstract: Performing data clustering in a model property vector space. Input data is received comprising a plurality of data instances in a data vector space. A model property vector specification is defined for a model vector. Information is identified from the input data, and a model property vector is created in the model property vector space for each of the plurality of data instances. A target number of clusters is identified and used to perform a data clustering procedure. An output is generated comprising a plurality of data segments and one or more clustering rules. For each data cluster, a predictive model is constructed for each data segment of the plurality of data segments.

Abstract: Embodiments for self-managed adaptable models for prediction systems by one or more processors. One or more adaptive models may be applied to data streams from a plurality of data sources according to one or more data recipes such that the one or more adaptive models predict a plurality of target variables.

Abstract: Embodiments for network reconstruction from message data by a processor. A digital map may be created using one or more messages of a plurality of vehicles obtained at a plurality of control points of a route network. The digital map may be analyzed to estimate a feasibility of simultaneous trajectories of the plurality of vehicles between selected locations in the route network.

Abstract: Embodiments for ensemble policy generation for prediction systems by a processor. Policies are generated and/or derived for a set of ensemble models to predict a plurality of target variables for streaming data such that the plurality of policies enables dynamic adjustment of the prediction system. One or more of the policies are updated according to one or more error states of the set of ensemble models.

Abstract: A method, apparatus and computer program product for solving an optimization model by automatically creating alternative formulations, and solving those with parallel solution approaches communicating with each other. The method: automatically generates alternative formulations for a given optimization model; executes parallel communicating solution approaches in a parallel computing infrastructure in order to solve a given set of alternative model formulations; utilizes a mechanism to automatically detect the model structure and a mechanism to automatically detect the appropriate solution approach(es) for a given model structure, and to launch multiple parallel solution approaches at existing optimization solvers. The system and methods enable communication between parallel solution approaches in order to improve performance. The system communicates information between the parallel solution approaches during a solve process, in order to improve performance.

Abstract: Embodiments relate to generating a route plan. A method of generating a route plan is provided. The method receives a route planning request that includes a starting location, a destination location, a desired arrival time, and a set of user preferences. The method obtains transport service information that includes schedules of a plurality of transport services provided for a geographic region including the starting location and the destination location. The method determines a set of transport services for each of a plurality of possible intermediate locations between the starting and destination locations. The sets of transportation services provide a maximum probability of arriving at the destination location before the desired arrival time as long as a user takes a first-arriving transportation among the set of transport services at each intermediate location while traveling from the starting location to the destination location.

Abstract: Embodiments relate to generating a route plan. A method of generating a route plan is provided. The method receives a route planning request that includes a starting location, a destination location, a desired arrival time, and a set of user preferences. The method obtains transport service information that includes schedules of a plurality of transport services provided for a geographic region including the starting location and the destination location. The method determines a set of transport services for each of a plurality of possible intermediate locations between the starting and destination locations. The sets of transportation services provide a maximum probability of arriving at the destination location before the desired arrival time as long as a user takes a first-arriving transportation among the set of transport services at each intermediate location while traveling from the starting location to the destination location.

Abstract: A system and method is provided for consistent price optimization in multi-modal transportation networks. A corridor is constructed for each origin-destination pair of a transportation network based on one or more parameters. Monotonicity constraints and triangle constraints are generated for each origin-destination pair. An objective function is constructed and convexified using point-price elasticity for consistent price optimization. The one or more parameters and coefficients for a mathematical optimization program are then computed and the mathematical optimization problem is solved for a consistent optimal pricing scheme.

Abstract: A system and method is provided for revenue management in multi-modal transportation networks. A corridor is constructed for each origin-destination pair of a transportation network based on one or more parameters. Monotonicity constraints and triangle constraints are generated for each origin-destination pair. An objective function is constructed and convexified using point-price elasticity for consistent price optimization. The one or more parameters and coefficients for a mathematical optimization program are then computed and the mathematical optimization problem is solved for a consistent optimal pricing scheme.

Abstract: Robust inventory management for a supply chain network with multiple nodes may include generating a time-phased inventory deployment plan based on extreme samples and dynamic supply chain structure. The extreme samples of demand and supply chain scenarios, and dynamic supply chain structure including one or more resource constraints associated with one or more nodes in the supply chain network may be received from a user.