Abstract: Some embodiments provide systems to determine contextual information comprising: an intent mining system that receive inquiry content that does not include personal identification information (PII) and is configured to determine an estimated intent information being sought by an intended recipient, identify a mapping to a sub-set of supplemental keywords corresponding to the intent information; and identify historic inquiries associated with actual historic product purchases relevant to the inquiry content and supplemental keywords, and obtain a listing of products associated with the inquiry content; a product association system that identifies a set of multiple products that each have a purchase threshold relationship with one or more products from the determined listing of products, and generate an enhanced listing of products; a topic extraction system that evaluates associations between product parameters of the enhanced listing of products to identify multiple associated topics and corresponding topic c

Abstract: Systems, method, and computer-readable mediums for automated text classification, and particularly a mechanism for performing binary classification using only a set of positive labeled data as training data and having a large set of unlabeled data, where the algorithm can function without any information regarding the negative class. The disclosed classification systems and methods may use a text classification process which automatically classifies text based on the current positive training data available, but identifies additional words which can be added to the positive training data such that future iterations of the text classification can better identify the positive class of text.

Abstract: A system can include a database and a computing device. The computing device is configured to receive an item recommendation request corresponding to an asset from an analyst device and select a set of item identifiers of a plurality of item identifiers. An associated published timeframe of the selected item identifiers is related to a present timeframe. The computing device is further configured to determine a composite similarity value for each item identifier of the set of item identifiers comparing a similarity of the asset to each item identifier of the set of item identifiers. The computing device is also configured to generate an item recommendation list including each item identifier of the set of item identifiers with a corresponding composite similarity value above a threshold value and transmit the item recommendation list to the analyst device for display.

Abstract: A set of reportable customer cases is obtained, and a set of non-reportable cases is obtained from un-labeled customer cases. Matrices of words from the non-reportable set and reportable set are obtained. A comparison is made between the reportable corpus and the non-reportable corpus. For words that are in the reportable corpus and not in the non-reportable corpus more than a predetermined number of times, words are identified as core keywords and put it in a keyword set. Iterations are performed on the set to refine the set and improve its accuracy and create a dictionary using both lexicon and contextual nearness of words.

Abstract: Examples a system for customized travel planning management. The system extracts relevant travel-related data from travel-related provider contracts. The extracted relevant travel-related data and historical travel usage data are analyzed to calculate a market share for each provider. A booking manager identifies recommended travel-related provider pairs associated with a set of travel dates within a predetermined range of a user-selected preferred date of travel associated with a user-selected source-to-destination pair based on the calculated market share for each provider and user-provided travel preferences. The system books the user's selected accommodations provider and travel provided on a recommended booking date. An optimization component identifies recommended future negotiation terms associated with at least one provider in the set of travel-related providers based on the historical travel usage data, historical transaction data and historical contract compliance data.

Abstract: Examples provide a system for detecting anomalies in a dataset. The system includes one or more processors and a memory storing the dataset. The one or more processors are programmed to identify a first set of data points in a cluster, identify a second set of data points outside of the cluster as noisy data points, and determine whether each of the noisy data points is an anomaly by: determining a distance between the noisy data point and other data points in the dataset, ranking the distances between the noisy data point and the other data points, and applying a weight to each of the ranked distances to determine an outlier value for the noisy data point. When the outlier value for the noisy data point exceeds a threshold, the noisy data point is identified as an anomaly, and result is displayed in a user interface.

Abstract: Systems, method, and computer-readable mediums for automated text classification, and particularly a mechanism for performing binary classification using only a set of positive labeled data as training data and having a large set of unlabeled data, where the algorithm can function without any information regarding the negative class. The disclosed classification systems and methods may use a text classification process which automatically classifies text based on the current positive training data available, but identifies additional words which can be added to the positive training data such that future iterations of the text classification can better identify the positive class of text.

Abstract: Examples provide a system for detecting anomalies in a dataset. The system includes one or more processors and a memory storing the dataset. The one or more processors are programmed to identify a first set of data points in a cluster, identify a second set of data points outside of the cluster as noisy data points, and determine whether each of the noisy data points is an anomaly by: determining a distance between the noisy data point and other data points in the dataset, ranking the distances between the noisy data point and the other data points, and applying a weight to each of the ranked distances to determine an outlier value for the noisy data point. When the outlier value for the noisy data point exceeds a threshold, the noisy data point is identified as an anomaly, and result is displayed in a user interface.