Abstract: In an approach to improve additive manufacturing embodiments receive, by a sensor set, data associated with an object or a predetermined area, and retrieve, by a knowledge corpus, historic data associated with the object or the predetermined area. Further, embodiments identify a defect on or within an object based on an identified difference in the received data and the historic data and identify, by the sensor set, a target area on the object to repair the defect. Additionally, embodiments, create, by a context-aware robotic system, a physical support around the target area, and repair, by an additive manufacturing mechanism and the physical support, the defect by applying three-dimensional printing-based rectification to the defect.

Abstract: In an approach to improve the management of operating vehicles through smart contracts, embodiments generate a priority score based on received sensor feeds from a vehicle, co-located vehicles, and a smart contract rule. Further, embodiments assign the priority score to the vehicle and the co-located vehicles and the co-located vehicles and identify that the assigned priority score of the vehicle is higher than the co-located vehicles. Additionally, embodiments manage an operation of the co-located vehicles through a computing device within the co-located vehicles based on the smart contract rule and the priority score and create a priority lane for the vehicle by repositioning the co-located vehicles.

Abstract: A method, computer system, and a computer program product is provided for authenticating a user. In one embodiment, a method that selects a selecting a username associated with a user. A plurality of characters are provided to be selected and a set of typing styles relating to at least one of these characters are selected to create a password for the user. Subsequently, the username and the password are stored in a database. The password includes the typing styles. The user can then access a resource through authentication by providing a username and password that includes the selected typing styles. The stored username and password is retrieved from the database and checked against user provided information and the user is authenticated when the user provided information and retrieved information are a match.

Abstract: Systems, methods, and computer programming products for dynamically managing the uninstallation and/or re-installation of software applications stored or accessed by a computing system, including mobile devices. Management of the applications by the system can be periodically managed automatically or based on recommendations. Management of applications being uninstalled or reinstalled may be determined based on a rate a user accesses the application and/or data published or accessible by an application storefront, such as user reviews, storefront rankings, user feedback and uninstallation rates of the applications by other users. Applications experiencing a decreased level of average user satisfaction below a predetermined threshold can be proposed for deletion or automatically deleted. Replacement of underperforming or unsatisfactory applications with alternative applications having similar functionality but a higher rate of user satisfaction can be recommended or installed.

Abstract: According to one embodiment, a method, computer system, and computer program product for user authentication. The embodiment may include receiving, from a first device, multiple location coordinates of the first device. The embodiment may include storing, on a second device, a second moving window comprising last n location coordinates of the multiple location coordinates. The embodiment may include receiving, from the first device, a request to access the second device, wherein the request comprises log-in credentials and a first hash value. The embodiment may include computing, on the second device, a second hash value based on the second moving window. The embodiment may include verifying the log-in credentials. The embodiment may include comparing the first hash value and the second hash value. In response to the first and the second hash values being equal, and the log-in credentials being verified, the embodiment may include granting access.

Abstract: A method, computer system, and a computer program product for optimizing social collaboration is provided. The present invention may include identifying content within a social collaboration history with a high level of engagement. The present invention may include generating one or more groups of unique topic keywords based on the identified content. The present invention may include receiving a potential post from a user. The present invention may include identifying an overlap between the potential post and at least one of the one or more groups of unique topic keywords. The present invention may include providing one or more recommendations to the user.

Abstract: A sentiment analysis scheduling method, system, and computer program product include analyzing prior sentiments based on past events, building a personalized data model with a categorized event type and a sentiment outcome based on the prior sentiments, analyzing an upcoming event content and predicting a potential sentiment outcome for the upcoming event based on the personalized data model, and rearranging an order of future events to achieve the predicted potential sentiment outcome for the upcoming event.

Abstract: A computer system selects features of a dataset for predictive modeling. A first set of features that are relevant to outcome are selected from a dataset comprising a plurality of cases and controls. A subset of cases and controls having similar values for the first set of features is identified. The subset is analyzed to select a set of additional features relevant to outcome. A first and second predictive model are evaluated to determine that the second predictive model more accurately predicts outcome, wherein the first predictive model is based on the first set of features and the second predictive model is based on the first set of features and the additional features. The second predictive model is utilized to predict outcomes. Embodiments of the present invention further include a method and program product for selecting features of a dataset for predictive modeling in substantially the same manner described above.

Abstract: Utilization data of a computer by a user during a session is gathered. A domain in which the user is utilizing the computer during the session is identified as reflected by the utilization data. Competence data on how competent the user is with the domain is gathered. The competence data relates to how the user interacts with the computer during the session. A competence level of the user for the domain is determined based on the competence data.

Abstract: A plurality of events are extracted from a plurality of electronic health records associated with a first patient. The extracted plurality of events are analyzed to identify a plurality of stimulus events and a plurality of response events. An association between a first stimulus event and a first response event is determined. A stimulus-response (SR) variable is generated for the first patient based at least in part on the determined association, and the generated SR variable is integrated into one or more predictive cognitive models.

Abstract: A computer-implemented method for transaction authorization is disclosed. The computer-implemented method includes receiving a transaction request from a user to access a resource. The computer-implemented method further includes determining historical biometric data for the user. The computer-implemented method further includes determining current biometric data for the user at a time the transaction request is received. The computer-implemented method further includes determining whether the historical biometric data for the user matches the current biometric data for the user at the time the transaction request is received. The computer-implemented method further includes responsive to determining that the historical biometric data for the user matches the current biometric data for the user at the time the transaction request is received, authorizing the transaction request to access the resource.

Abstract: A method of providing, by a computing device, access to a user of sections of an electronic document. The method includes receiving, by a computing device, a computerized image of a user accessing an electronic document. The computing device further accesses a facial recognition database and compares the computerized image to one or more entries in the facial recognition database to determine an identity of the user. The user is provided access to one or more sections of the electronic document based upon the identity of the user.

Abstract: A computer-implemented method, computer program product, and computer system for preventing losses due to mismatches during checkouts in a store. The computer system causes one or more sensors to capture one or more attributes of an item being checked out by a customer. The computer system matches the captured one or more attributes to one or more attributes corresponding to one of a barcode scanned, a number keyed in, and an item name chosen by the customer. The computer system pauses a checkout process, in response to a mismatch. The computer system calculates a difference between a price corresponding to one of the barcode, the number, and the item name and an actual price of the item. The computer system, in response to determining a significant loss occurring to the store, notifies the store to correct the mismatch and processes a transaction of the item at the actual price.

Abstract: Obtain covariates and an outcome data for a population. Partition the population into a plurality of subgroups. Produce outcomes predictions by applying a machine learning model to the covariate data for the population. Establish performance measures based on the outcomes predictions. Compare the performance measures for at least one subgroup to the performance measures for at least one other subgroup. Identify an outlying subgroup for which the machine learning model produces performance measures that are different than the performance measures for one or more other subgroups. Optionally, retrain the machine learning model on additional covariate and outcomes data for the outlying subgroup.

Abstract: Systems, methods, and computer programming products for dynamically managing the uninstallation and/or re-installation of software applications stored or accessed by a computing system, including mobile devices. Management of the applications by the system can be periodically managed automatically or based on recommendations. Management of applications being uninstalled or reinstalled may be determined based on a rate a user accesses the application and/or data published or accessible by an application storefront, such as user reviews, storefront rankings, user feedback and uninstallation rates of the applications by other users. Applications experiencing a decreased level of average user satisfaction below a predetermined threshold can be proposed for deletion or automatically deleted. Replacement of underperforming or unsatisfactory applications with alternative applications having similar functionality but a higher rate of user satisfaction can be recommended or installed.

Abstract: A computer-implemented method for obfuscating sensitive information associated with mail delivery is disclosed. The computer-implemented method includes identifying that a piece of mail directed towards a potential recipient includes a particular type of sensitive information. The computer-implemented method further includes selecting a mail obfuscation policy for the particular type of sensitive information based on the particular type of sensitive information. The computer-implemented method further includes performing an obfuscation action with respect to the particular type of sensitive information based on the selected mail obfuscation policy.

Abstract: A method, computer system, and a computer program product for account security is provided. The present invention may include analyzing one or more financial accounts of a user and assigning a risk threshold to each of the one or more financial accounts. The present invention may include monitoring a vulnerability of each of the one or more financial accounts, wherein the vulnerability is monitored using a vulnerability score, the vulnerability score being generated based on user data. The present invention may include determining the risk threshold has been exceeded for at least one financial account based on a comparison of the vulnerability score and the risk threshold of the at least one financial account. The present invention may include preventing access to the at least one financial account in which the risk threshold has been exceeded.

Abstract: Correspondence information recorded by trusted entities is maintained up to date by monitoring user activity for location-based transaction data and determining by a machine learning algorithm when a piece of correspondence information has changed. When a change is detected, effected entities receive proposals for alternative temporary correspondence and formal change requests are submitted.

Abstract: A plurality of attributes are extracted from a plurality of electronic health records, where each electronic health record is associated with a patient in a plurality of patients. Additionally, a training data set and a scoring data set are generated based on the plurality of attributes, and a patient similarity model is trained based on the training data set. A precision cohort is identified, where the precision cohort includes patients in the plurality of patients from the scoring data set that are similar to a first patient based on an electronic health record of the first patient and the similarity model. At least one result statistic for each of a plurality of treatments given to patients in the precision cohort is determined, and a first treatment of the plurality of treatments is selected for the first patient based at least in part on the determined result statistics.

Abstract: Taking security actions according to calculated sensitivity levels of objects. Sensitivity levels are determined according to learned security measures taken on objects having certain content. Security actions are taken upon determining that an object in view of recently added content has an actionable sensitivity level. Additional considerations apply to baseline aspects of the object as well as ongoing changes to the baseline considerations.