Abstract: Aspects if the disclosure are directed towards multi-step forecasting via temporal aggregation. An example embodiment includes a method the includes receiving a time series including a first time step value and a second time step value. The method can further include generating a temporally aggregated time series by summing the first time step value and the second time step value to create a third time step value. The method can further include calculating a first set of input values and a second set of input values from the temporally aggregated time series. The method can further include forecasting a fourth time step value using the first set of input values and the second set of input values, and a fifth time step using the second set of input values from the temporally aggregated time series.

Abstract: A time series forecasting system is disclosed that obtains a time series forecast request requesting a forecast for a particular time point. The forecast request identifies a primary time series dataset for generating the requested forecast and a set of features related to the primary time series dataset. The system provides the primary time series dataset and the set of features to a model to be used for generating the forecast. The model computes a feature importance score for one or more features and selects a subset of features based on their feature importance scores. The model determines attention scores for a set of data points in the primary time series dataset based on the selected subset of features. The system predicts an actual forecast for the particular time point based on the attention scores and outputs the actual forecast and explanation information associated with the actual forecast.

Abstract: A computing device may access a graph comprising one or more model nodes, one or more dataset nodes, and one or more edges, the model nodes having a plurality of features. The device may add one or more test dataset nodes and test edges to the graph. The device may perform a series of iterative steps until a threshold is reached. For each iterative step: a selection probability is determined, the selection probability being based at least in part on a plurality of selection criteria; a particular model node is selected, the particular model node being selected based at least in part on the selection probability; the selection criteria is updated based at least in part on the particular model; and the plurality of features are updated based at least in part on the particular model. The device may provide the particular model node selected in the last iterative step.

Abstract: The present embodiments relate to using feature engineering to generate time-varying features via metadata. A first exemplary embodiment provides a method for performing feature engineering to generate time-varying features. The method can include receiving a first value and a second value of the time-series data. The method can further include receiving metadata that describes a relationship between the first value and the second value. The method can further include detecting the relationship between the first value and the second value based on the metadata. The method can further include generating, a time-varying feature from a combination of the first value and the second value based on the relationship detected from the metadata. The method can further include generating, by implementing the machine learning forecasting model, a forecasted value for the time-series data based on the time-varying feature.

Abstract: The present embodiments relate to generating input parameters for selecting a forecasting model. An example method includes a computing device receiving a time series comprising a plurality of data points, wherein each data point of the time series comprises a time associated with the data point and a value. The device can identify a first season and a second season from the time series, wherein a length of the first season is a factor of a length of the second season. The device can estimate a Fourier order and a seasonality mode for the first season based at least in part on the length of the first season and the length of the second season. The device can select a forecasting model to forecast a value of a future time step of the time series based at least in part on the Fourier order and the seasonality mode.

Abstract: Techniques are described for providing explanation information for time series-based predictions made using statistical models, such as linear statistical models, examples of which include various Exponential Smoothing models, Autoregressive Integrated Moving Average (ARIMA) models, and others. For a forecast predicted by a statistical model that has been trained upon and/or fit to a set of historical times series data points, an explanation is generated for the forecast, where the explanation for the forecast includes information indicative of the importance or impact or influence of individual time series data points in the set on the forecast. The explanation for the forecast may be output to a user along with the forecast. This enables the user to have some visibility into why the particular forecast was predicted by the statistical model.

Abstract: A time series forecasting service system is disclosed. The system identifies a set of cross-validation parameters to be used for cross-validating a model to be used for generating a requested forecast. The requested forecast includes a time series dataset and a forecast horizon identifying a number of time steps for which a forecast is to be made using the time series dataset. The system identifies an objective function to be minimized for determining optimal values for the set of cross-validation parameters and identifies constraints for the cross-validation parameters. The system uses an optimization technique to determine the optimal values for the cross-validation parameters. The optimization technique performs processing that determines the optimal values by minimizing the objective function while satisfying the set of constraints. The system uses the optimal values for the cross-validation parameters to perform cross-validation of the model to be used for making the requested forecast.

Abstract: A computer-implemented method and an apparatus facilitate on-demand building of predictive models. Data corresponding to a plurality of customers is retrieved from data sources and a training data sample and a testing data sample are generated from the retrieved data. Variables for developing the predictive model are identified from the retrieved data and are subjected to any of structured categorical variable binning, unstructured categorical variable binning, and numeric variable binning to generate transformed variables. The transformed variables and the training data sample are used to develop predictive models. The developed predictive models are tested using the testing data sample and scores are generated corresponding to the developed predictive models. A predictive model is selected from among the developed predictive models based on the scores. The selected predictive model is published on a prediction platform to facilitate prediction of outcomes related to customers of the enterprise.

Abstract: A method of iterative negotiation for improved production planning between one or more purchasers and suppliers in a supply chain. The method includes a purchaser in a supply chain generating a request schedule that is communicated to a supplier. In response to the request schedule the supplier generates a commit schedule and communicates it back to the purchaser. Through the iterative negotiation process (ask-answer) one or more interpolation constraints are generated based on the supplier's commit schedules. Upon completion of the ask-answer process purchaser solves a final advanced planning system (APS) based on said one or more interpolation constraints and generates a final production plan. The invention can be employed to integrate the collaboration among purchasers and suppliers with an advanced planning system for optimizing established planning objectives (e.g. customer service, short lead times, low inventory, and prioritized allocation of supply and capacity).

Abstract: A method of iterative negotiation for improved production planning between one or more purchasers and suppliers in a supply chain. The method includes a purchaser in a supply chain generating a request schedule that is communicated to a supplier. In response to the request schedule the supplier generates a commit schedule and communicates it back to the purchaser. Through the iterative negotiation process (ask-answer) one or more interpolation constraints are generated based on the supplier's commit schedules. Upon completion of the ask-answer process purchaser solves a final advanced planning system (APS) based on said one or more interpolation constraints and generates a final production plan. The invention can be employed to integrate the collaboration among purchasers and suppliers with an advanced planning system for optimizing established planning objectives (e.g. customer service, short lead times, low inventory, and prioritized allocation of supply and capacity).